# Do Personality Traits Interfere? Geometric Limitations of Steering in Large Language Models

arXiv: https://arxiv.org/abs/2602.15847 · HTML: https://mlsanity.com/paper/2602.15847/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Placed in Activation steering methods, one of 13 directions in Mechanistic interpretability.
- Builds on 11 of its 18 references that are in the map.
- First posted on arXiv 23 Jan 2026.

## Placed in

- Mechanistic interpretability / [Activation steering methods](https://mlsanity.com/mechinterp/activation-steering-methods/)

## Builds on (most cited first, 11 of 11)

- [Null It Out: Guarding Protected Attributes by Iterative Nullspace Projection](https://mlsanity.com/paper/2004.07667/) (2020)
- [Persona Vectors: Monitoring and Controlling Character Traits in Language Models](https://mlsanity.com/paper/2507.21509/) (2025)
- [LEACE: Perfect linear concept erasure in closed form](https://mlsanity.com/paper/2306.03819/) (2023)
- [PersonaLLM: Investigating the Ability of Large Language Models to Express Personality Traits](https://mlsanity.com/paper/2305.02547/) (2023)
- [Personality Traits in Large Language Models](https://mlsanity.com/paper/2307.00184/) (2023)
- [BIG5-CHAT: Shaping LLM Personalities Through Training on Human-Grounded Data](https://mlsanity.com/paper/2410.16491/) (2024)
- [Personality Alignment of Large Language Models](https://mlsanity.com/paper/2408.11779/) (2024)
- [Evaluating Personality Traits in Large Language Models: Insights from Psychological Questionnaires](https://mlsanity.com/paper/2502.05248/) (2025)
- [Exploring the Personality Traits of LLMs through Latent Features Steering](https://mlsanity.com/paper/2410.10863/) (2024)
- [Personality Vector: Modulating Personality of Large Language Models by Model Merging](https://mlsanity.com/paper/2509.19727/) (2025)
- [Activation-Space Personality Steering: Hybrid Layer Selection for Stable Trait Control in LLMs](https://mlsanity.com/paper/2511.03738/) (2025)

## Built on by (most cited first, 5 of 5)

- [Prompt-Activation Duality: Improving Activation Steering via Attention-Level Interventions](https://mlsanity.com/paper/2605.10664/) (2026)
- [Persona Cartography: Charting Language Model Personality Traits in Weight Space](https://mlsanity.com/paper/2607.07916/) (2026)
- [Persona Non Grata: Single-Method Safety Evaluation Is Incomplete for Persona-Imbued LLMs](https://mlsanity.com/paper/2604.11120/) (2026)
- [Steering Interference Reflects the Model's Defaults, Not the Behavior Directions](https://mlsanity.com/paper/2609.06951/) (2026)
- [Contrastive Covariance Subspaces for Activation Steering](https://mlsanity.com/paper/2610.14025/) (2026)

## Abstract (arXiv)

Personality steering in large language models (LLMs) commonly relies on injecting trait-specific steering vectors, implicitly assuming that personality traits can be controlled independently. In this work, we examine whether this assumption holds by analysing the geometric relationships between Big Five personality steering directions. We study steering vectors extracted from two model families (LLaMA-3-8B and Mistral-8B) and apply a range of geometric conditioning schemes, from unconstrained directions to soft and hard orthonormalisation. Our results show that personality steering directions exhibit substantial geometric dependence: steering one trait consistently induces changes in others, even when linear overlap is explicitly removed. While hard orthonormalisation enforces geometric independence, it does not eliminate cross-trait behavioural effects and can reduce steering strength. These findings suggest that personality traits in LLMs occupy a slightly coupled subspace, limiting fully independent trait control.