Skip to content
Apart Research
Apart Research
Contact us
Sprint projectAug 17, 2026Changsha, Hunan Province, China

Same Game, Different Feelings: Persona Prompts Modulate How Feedback Reshapes Internal Emotion Trajectories

Lia Lind · Team Lia

Submitted to Digital Minds Research Sprint. Sprint projects are early-stage work by participants, not Apart Research publications.

Read the report

Report: Same Game, Different Feelings: Persona Prompts Modulate How Feedback Reshapes Internal Emotion Trajectories

Open in a new tab (opens in new tab)
Code (opens in new tab)
Share

We investigate whether persona prompts change not just what a language model says, but how its internal representations respond to ongoing experience. Using Qwen2.5-1.5B-Instruct, we condition twelve persona prompts (crossing Extraversion × Neuroticism) in an adversarial Mastermind game engineered for five consecutive failures, under three feedback conditions: game results only, results plus supportive encouragement, and results plus length-matched neutral filler. We track activation trajectories along externally defined emotion directions (joyful, grief-stricken, furious) via cosine projection. Supportive feedback reliably reshapes trajectories relative to neutral filler—but not uniformly: it buffers joyful decline and furious rise while unexpectedly steepening grief-stricken rise, suggesting cosine projection onto emotion directions cannot be read as a simple mood indicator. Persona prompts further modulate the feedback effect at roughly one-tenth its magnitude, with six of nine planned contrasts surviving Holm correction. We release the experimental framework for reuse.

Reviews

Judging this Sprint?

Review this project

Your public critique appears on this page without your name. Your private critique is not published; only the Apart team reads it. If you agree below, we share your review with grantmaking.ai (opens in new tab) and the Transformative AI Fund so strong projects can be funded.

Not shown on this page.

Shown on this page, without your name.

Only the Apart team reads this, and funders if you agree below.

Share my name publicly on grantmaking.ai *
Share my private critique with funders *

How much would this matter for the field if it worked? How innovative is it? For scores of 4-5: is this actually new to the field, or replicating recent work?

Scoring guide
  1. 1Negligible. No clear problem addressed, or no meaningful novelty.
  2. 2Limited. Addresses a real problem but with a generic or well-trodden approach. Incremental at best.
  3. 3Moderate. Clear problem with a reasonable approach; some novelty in framing or method beyond routine application of existing tools.
  4. 4Significant. Important problem with an original approach, or identifies a neglected problem area. A valuable contribution others could build on.
  5. 5Exceptional. Tackles a critical problem with a genuinely novel approach, or opens a new research direction. Clear theory of change. You'd be excited to share this with researchers in the area.

How sound are methodology, implementation, and findings?

Scoring guide
  1. 1Seriously flawed. Methodology broken, results uninterpretable, or implementation doesn't work.
  2. 2Weak. Approach has significant gaps: missing validation, flawed experimental design, or incomplete implementation.
  3. 3Competent. Technically solid given the short duration. Methodology makes sense, results are interpretable, limitations acknowledged, work builds toward clear conclusions.
  4. 4Strong. Thorough methodology with convincing validation. Results clearly support conclusions. Immediately useful for future work.
  5. 5Exceptional. Ambitious scope executed rigorously. Surprising findings, novel methods, or unusually robust validation.

How clearly are work, findings, and impact potential communicated?

Scoring guide
  1. 1Incomprehensible. Cannot determine what the project is actually claiming or doing.
  2. 2Hard to follow. Key information buried, missing, or diluted by excessive length. Significant effort to extract main points.
  3. 3Clear enough. Can understand the problem, approach, and results without undue effort. Core content clearly present: problem, method, findings, limitations.
  4. 4Well presented. Easy to follow, well-structured, appropriate level of detail. Target audience would get it quickly.
  5. 5Exceptionally clear. A pleasure to read. Complex ideas made accessible. Could serve as a model for how to present this type of work.

  1. The longitudinal design provides a view of emotional vector shifts across several conditions, and the report clearly and carefully discusses how to interpret the results. There is an important confound in the current set up. The measured state reflects not only the model's reaction to the manipulated text, but also its representation of the text itself. Untangling these components is key to isolating the desired effect.

Cite this project

@misc{lind2026same,
  title = {{Same Game, Different Feelings: Persona Prompts Modulate How Feedback Reshapes Internal Emotion Trajectories}},
  author = {Lia Lind},
  year = {2026},
  month = aug,
  note = {Submitted to Digital Minds Research Sprint, an Apart Research Sprint},
  howpublished = {\url{https://apartresearch.com/sprints/projects/same-game-different-feelings-persona-prompts-modulate-how-feedback-reshapes-internal-emotion-trajectories-18xb}},
  url = {https://apartresearch.com/sprints/projects/same-game-different-feelings-persona-prompts-modulate-how-feedback-reshapes-internal-emotion-trajectories-18xb}
}

More from Digital Minds Research Sprint

All 233 entriesBrowse all projects

Build something like this at the next Sprint

AI Collusion Research Sprint · Oct 23 - 25, 2026