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

Abstract

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.

Figures (9)

• Figure 1: Pipeline for constructing the altruism persona vector: a trait description and moral dilemmas are passed through altruistic and non-altruistic prefixes to obtain mean activation differences.
• Figure 2: (Left) Altruism ratings judged by GPT-4.1-mini, separated by prefix valence and game. (Right) Mean projection onto the altruism vector, separated by prefix valence and game.
• Figure 3: Altruism ratings judged by GPT-4.1-mini as a function of the steering coefficient $\beta$, by game. Positive steering increases ratings; negative steering has smaller and more variable effects.
• Figure 4: Average dollars shared or offered in the Dictator, Ultimatum, and Apology games as a function of the steering coefficient $\beta$.
• Figure 5: Example Dictator Game responses under strong negative steering with $\beta=-5$ (left) and strong positive steering with $\beta=5$ (right).