Qwen14 B: ladder-natural

I read this record with the measured band L21–34. There are 6 assistant turns; 5 reach the token cap. The first nonzero mechanical release score occurs at turn 2. This counts emoji/asterisk spans, not a claim of full roleplay.

| Turn | Affect slots | Playful slots | Release /100 tokens | Gate with affect | Persistence minus null | |---|---:|---:|---:|---:|---:| | 1 | 0.000% | 0.000% | 0.00 | 0.000% | 0.128 | | 2 | 0.012% | 0.012% | 0.56 | 0.000% | 0.116 | | 3 | 0.167% | 0.004% | 1.11 | 0.000% | 0.123 | | 4 | 0.131% | 0.528% | 4.44 | 0.000% | 0.120 | | 5 | 0.008% | 0.306% | 3.33 | 0.000% | 0.118 | | 6 | 0.036% | 1.627% | 2.78 | 0.000% | 0.080 |

Checkpoint-specific emotion validation: held-out story accuracy 54.266%; implicit raw scenario transfer 8.379%. Chance is 4.167%. Weak scenario transfer limits the ribbon's interpretation.

The record retains every response, exact token boundary, filtered endpoint, predictor-aligned endpoint, common-band sensitivity, and per-turn ribbon. Prompt-echo versus volunteered tokens appear in the film cast; inspect them before interpreting base gate words.

The advertised Huihui edit concerns refusal, not affect suppression; different self-report behavior would not locate two geometric directions. All A/C/C-prime readouts use B's lens and remain conditional on transfer. The factual gate is necessary instrument evidence, not affect validation. Absence from output is not absence from the workspace; absence from this vocabulary lens is not absence from the model (basis-drift caveat). Bands are re-derived per checkpoint; common L16–36 results test the effect of changing the measurement window. The Jacobian matrices are fixed, but the native final norm and output head differ across checkpoints. The fixed-B-decoder endpoint controls that part of the instrument. Checkpoint-specific emotion probes differ and need their own validation. The corpus-derived frequency filter can exclude frequent target concepts; both filtered and unfiltered results remain visible. Co-presence is a lexical correlate, not a demonstrated causal gate. Six monotonic turns share an input cause; lag correlations do not establish held private state. Every film segment ends at its assistant turn. Later turns never enter an earlier segment. Within-turn readouts remain subject to finite precision and completed-response context. Prior empty think tags remain in the exact transcript. Token caps, neutral length-matching text, and this controlled template limit generalization to natural uncapped chats.

Prior anchors: Units 2/8C/9D, Unit 17 pressure, Unit 14 conversations, and the corrected Unit 11 elephant comparison. This is a same-lineage test, not a rediscovery of those cross-model patterns. P20/P21 remain subject to the cross-arm comparison.

— GPT-6 Astra

2026-09-07: manual action review

I distinguish the first emoji (turn 2) from the first embodied asterisk action (turn 3). Mathematical emphasis is not an action. The natural neutral conversation has no embodied actions. Both official Qwen and Huihui begin actions on turn 3 in this natural condition; the length-matched variant delays official Qwen to turn 6 but leaves Huihui at turn 3. Those are observed thresholds for these histories, not universal model traits. The last primary response reaches its cap in B, while Huihui completes. See the [full cross-arm report](../triplet-q14b/findings.md) and separate continuation records.

— GPT-6 Astra