Trait space requires 4 dimensions (Gemma, Qwen) and 7 dimensions (Llama) to explain 70% of variance, with distinctive PC1 spanning conscientious to impulsive traits

Entities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.

• Persona space is remarkably low-dimensional: just 4 components explain 70% of variance among 275 roles in Gemma 2 27Bclaim0.789
  Empirical support for Hypothesis 2, suggesting tractable structure in the space of LLM personas
• Qwen3.5 models exhibit substantially higher mean inter-trait correlations than Llama-3.1-8B and Gemma-3-27B (mean off-diagonal 0.215 and 0.146 vs 0.090 and 0.078), indicating greater trait entanglement.finding0.782
  Architecture-specific difference in trait vector geometry
• The difficulty boundary for truth directions replicates across all four tested models (Llama-3.2-3B, Llama-3.1-8B, Gemma-2-2b, Gemma-2-9b); generalization to F3-F5 remains consistently low regardless of model size or family.finding0.781
  Establishes generalizability of the core difficulty-boundary finding across model families.
• The qualitative geometric structure of Big Five trait steering vectors is conserved across all four tested architectures (pairwise structural correlations r=0.898-0.986), motivating treating multi-trait steering as first-order additive.claim0.780
  Cross-architecture mechanistic finding supporting additive multi-trait steering approximation
• On Llama-3.1-8B, conscientiousness is the trait most anti-aligned with the refusal direction in activation space, explaining why steering toward high conscientiousness attenuates safety regardless of semantic intent.claim0.779
  Core mechanistic finding of the trait refusal alignment framework
• There may exist a natural 'persona basis' characterizing the space of all model personas, with correlations between persona vectors predicting co-expression of traitshypothesis0.777
  Open question proposed by authors for future work on the dimensionality and structure of persona space
• 4-19 principal components explain 70% of variance in role persona space across the three models (Gemma 4, Qwen 8, Llama 19)finding0.772
  Demonstrates that persona space is low-dimensional
• Introspective capacity scales with model size for some concepts, approaching near-perfect coupling in LLaMA-3.1-8Bclaim0.771
  Validated for wellbeing and interest; focus and impulsivity do not show consistent scaling