Personas Seem to Shape How Models Represent Behaviours

Representation engineering extracts trait vectors from a default-assistant context for use as monitoring probes and steering directions. We re-extract these vectors under prompt-induced personas and find that the resulting representation depends materially on the active persona: the same trait (e.g., assertiveness) is encoded differently depending on which persona the model is inhabiting, and these differences are consistent across traits and personas. The dissimilarities between trait representations correspond to behavioural differences under steering and efficacy differences across probes. This implies that probes and steering vectors may degrade as one moves away from the standard assistant persona—precisely the regime where monitoring robustness is most needed. We conclude with a discussion of implications for AI safety.