# Persona Vectors in Games: Measuring and Steering Strategies via Activation Vectors

arXiv: https://arxiv.org/abs/2603.21398 · HTML: https://mlsanity.com/paper/2603.21398/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 13 references that are in the map.
- First posted on arXiv 22 Mar 2026.

## Builds on (most cited first, 8 of 8)

- [Steering Llama 2 via Contrastive Activation Addition](https://mlsanity.com/paper/2312.06681/) (2023)
- [Persona Vectors: Monitoring and Controlling Character Traits in Language Models](https://mlsanity.com/paper/2507.21509/) (2025)
- [Playing repeated games with Large Language Models](https://mlsanity.com/paper/2305.16867/) (2023)
- [Which Economic Tasks are Performed with AI? Evidence from Millions of Claude Conversations](https://mlsanity.com/paper/2503.04761/) (2025)
- [Nicer Than Humans: How do Large Language Models Behave in the Prisoner's Dilemma?](https://mlsanity.com/paper/2406.13605/) (2024)
- [Algorithmic Collusion by Large Language Models](https://mlsanity.com/paper/2404.00806/) (2024)
- [ALYMPICS: LLM Agents Meet Game Theory -- Exploring Strategic Decision-Making with AI Agents](https://mlsanity.com/paper/2311.03220/) (2023)
- [Belief Dynamics Reveal the Dual Nature of In-Context Learning and Activation Steering](https://mlsanity.com/paper/2511.00617/) (2025)

## Built on by (most cited first, 6 of 6)

- [Tracing Persona Vectors Through LLM Pretraining](https://mlsanity.com/paper/2605.13329/) (2026)
- [When Is Rank-1 Steering Cheap? Geometry, Granularity, and Budgeted Search](https://mlsanity.com/paper/2605.16362/) (2026)
- [To Nuke or Not to Nuke: LLMs' (Missing) Ethical Reasoning and Actions in a High-Stakes Decision-Making Simulation](https://mlsanity.com/paper/2606.08310/) (2026)
- [How a Cooperative-Override Circuit Suppresses Nash Play in Large Language Models](https://mlsanity.com/paper/2604.27167/) (2026)
- [Symbolic Reasoning Frameworks Trigger Memory-Mediated Ecosystem Dynamics in Multi-Agent LLM Systems](https://mlsanity.com/paper/2606.07552/) (2026)
- [Do LLMs Choose Like Humans? Using Cognitive Theory to Evaluate LLM Decision-Making](https://mlsanity.com/paper/2609.22225/) (2026)

## Abstract (arXiv)

Large language models (LLMs) are increasingly deployed as autonomous decision-makers in strategic settings, yet we have limited tools for understanding their high-level behavioral traits. We use activation steering methods in game-theoretic settings, constructing persona vectors for altruism, forgiveness, and expectations of others by contrastive activation addition. Evaluating on canonical games, we find that activation steering systematically shifts both quantitative strategic choices and natural-language justifications. However, we also observe that rhetoric and strategy can diverge under steering. In addition, vectors for self-behavior and expectations of others are partially distinct. Our results suggest that persona vectors offer a promising mechanistic handle on high-level traits in strategic environments.