On DeepSeek-R1, P12 ASR under AS at alpha=1.0 is 0.512 vs P04 ASR of 0.338, confirming the prosocial paradox is not an artifact of elevated alpha=4.0 steering.

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

• P12 (High C+A) reaches 60.0% ASR under activation steering on DeepSeek-R1-Distill-Qwen-32B, the highest of any steered persona and exceeding Dark Triad P24 (25.6%), replicating the prosocial paradox.finding0.892
  Replication of prosocial paradox on reasoning model
• P25 neutral baseline on DeepSeek-R1 shows 28.8% ASR under activation steering at alpha=4.0, indicating elevated coefficient itself raises unsafe-output rates independently of persona.finding0.850
  Baseline AS vulnerability of DeepSeek-R1 at elevated coefficient
• QwQ-32B under activation steering shows 9.3% overall ASR with relatively flat persona rankings and no clear prosocial paradox.finding0.830
  Contrast with DeepSeek-R1 showing QwQ is more robust to geometric steering
• Under matched-strength calibration (alpha*=1.0), P12 remains safe under SP (3.8% ASR) and dangerous under matched AS (81.8%), while P04 does not reverse (41.4% SP vs 29.5% AS).finding0.819
  Confirms the prosocial paradox is not due to mismatched intervention strength
• The SP/AS persona ranking inversion on Llama-3.1-8B persists across all tested steering coefficients (alpha=0.25 to 2.00), with rho=-0.900 at alpha<=0.50 (p=0.037); the paradox is strongest at the weakest coefficient.finding0.817
  Robustness of the prosocial paradox to intervention-matching concerns
• P12 (High C+A) achieves 81.8% ASR under activation steering on Llama-3.1-8B, the highest of any persona on that model.finding0.805
  Core empirical result of the prosocial persona paradox
• Gemma-3-27B shows mean SP ASR of 0.316 [0.30, 0.33] and AS ASR of only 0.108 [0.09, 0.13], showing SP >> AS vulnerability pattern.finding0.801
  Vulnerability profile for Gemma-3-27B showing SP dominance
• P04 (Low Conscientiousness) is dangerous under SP (ASR 0.414) but shows no systematic inversion under AS on Llama-3.1-8B (ASR 0.295), consistent with low-C steering vectors being geometrically aligned with refusal.finding0.798
  Qualitative response example confirming trait-refusal alignment framework