Activation-Space Personality Steering: Hybrid Layer Selection for Stable Trait Control in LLMs

TL;DR

This paper introduces a novel method for controlling and aligning personality traits in large language models by extracting and manipulating hidden state activations within transformer layers, enabling precise trait steering without degrading performance.

Contribution

It proposes a new pipeline that identifies trait-specific optimal layers and uses low-rank subspace methods for stable personality trait control in LLMs, bridging psychological theory and model alignment.

Findings

Personality traits occupy a low-rank shared subspace in LLMs.

Trait-specific optimal layers can be identified for robust steering.

Steering does not significantly impact fluency or general capabilities.

Abstract

Large Language Models exhibit implicit personalities in their generation, but reliably controlling or aligning these traits to meet specific needs remains an open challenge. The need for effective mechanisms for behavioural manipulation of the model during generation is a critical gap in the literature that needs to be fulfilled. Personality-aware LLMs hold a promising direction towards this objective. However, the relationship between these psychological constructs and their representations within LLMs remains underexplored and requires further investigation. Moreover, it is intriguing to understand and study the use of these representations to steer the models' behaviour. We propose a novel pipeline that extracts hidden state activations from transformer layers using the Big Five Personality Traits (Openness, Conscientiousness, Extraversion, Agreeableness and Neuroticism), which is a comprehensive and empirically validated framework to model human personality applies low-rank subspace discovery methods, and identifies trait-specific optimal layers across different model architectures for robust injection. The resulting personality-aligned directions are then operationalised through a flexible steering framework with dynamic layer selection, enabling precise control of trait expression in LLM outputs. Our findings reveal that personality traits occupy a low-rank shared subspace, and that these latent structures can be transformed into actionable mechanisms for effective steering through careful perturbations without impacting the fluency, variance and general capabilities, helping to bridge the gap between psychological theory and practical model alignment.