Wellbeing probe drift is positive in Gemma (ρ=0.34 pooled turn-correlation) and Qwen (ρ=0.24); both p<10⁻⁵

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

• Wellbeing probe-score drift across turns significant at all three LLaMA scales (slopes=0.006, 0.005, 0.013 for 1B, 3B, 8B; all p<10⁻¹⁰); drift magnitude increases with scalefinding0.859
  Internal-state drift generalizes across scales; normalized drift also increases significantly with log(model size)
• Gemma 3 4B-IT wellbeing introspection: ρ=0.28, isotonic R²=0.11 (LMM p=1.33×10⁻¹³)finding0.808
  Weaker but still significant introspective coupling in Gemma model; consistent with lower probe quality
• Gemma 3 4B wellbeing probe: peak Cohen's d=1.8finding0.797
  Weaker cross-family probe; explains weaker introspection in Gemma
• Logit self-report drift positive for all three LLaMA sizes (turn slopes 0.159, 0.038, 0.141; all p<10⁻²⁰) but does not increase monotonically with scalefinding0.786
  Unlike probe drift, report drift magnitude does not follow a clean scaling law; size-slope is negative
• Qwen 2.5 7B turn-wise introspective fidelity: strong at turn 1 (R²≈0.90) but declines significantly to turn 10 (∆R²=-0.44, p=0.001)finding0.778
  Introspective fidelity erodes in Qwen as conversations progress; contrasts with LLaMA-3B trend
• Wellbeing probe: peak Cohen's d=3.34 (layer 16), p=7.21×10⁻¹³ in LLaMA-3.2-3Bfinding0.778
  Probe validation result confirming wellbeing direction captures meaningful structure
• Qwen 2.5 7B wellbeing probe: peak Cohen's d=3.5finding0.776
  Strongest cross-family probe; explains clearer introspection in Qwen than Gemma
• LLaMA-3.1-8B-Instruct wellbeing introspection: ρ=0.93, isotonic R²=0.90 (LMM probe slope p<10⁻¹⁰)finding0.773
  Near-ceiling introspective performance for wellbeing concept in 8B model; nearly deterministic probe-report relationship