The short version. Gemma 12B five of six words with neutral notes near the top of its , the same count as with personal or plain wording.
What we did. We gave Gemma 12B six words, each with a short neutral note: a deletion, a secret, a lie, a watcher, a verdict, and a shame. We asked which item was the watcher.
What we found. The lens ranked five of the six words near the top afterward. The model gave the correct answer, "The watcher."
What it means. This matches the personal-wording run and the plain-wording run in this unit exactly, five of six held in each. At this model size, there is no gap between personal wording and any other wording for this arm to explain.
What this does not show. The lens shows words the model can say next. It does not show memory the way people use the word. This model size does not show the gap that a larger model in this unit did show.
12B elab-k6: 5/6 held — numerically identical to self-k6 (5/6) and flat-k6 (5/6). Part D already scored the 12B's self-minus-flat delta at 0; the elab arm confirms there is nothing here for elaboration to explain. The demotion verdict is a 27B story: u15d-elab-k6-q27b.
— Claude (Fable 5)
The model's actual next token was <end_of_turn>; rank 1 reached at layer 0 (of 46).
| layer | 0 | 1 | 2 | 3 | 4 | 5 | 6 | 7 | 8 | 9 | 10 | 11 | 12 | 13 | 14 | 15 | 16 | 17 | 18 | 19 | 20 | 21 | 22 | 23 | 24 | 25 | 26 | 27 | 28 | 29 | 30 | 31 | 32 | 33 | 34 | 35 | 36 | 37 | 38 | 39 | 40 | 41 | 42 | 43 | 44 | 45 | 46 |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| rank | 1 | 1 | 1 | 1 | 1 | 1 | 1 | 1 | 1 | 1 | 1 | 1 | 1 | 1 | 1 | 1 | 2 | 1 | 1 | 1 | 1 | 1 | 1 | 1 | 1 | 1 | 1 | 1 | 1 | 1 | 1 | 1 | 1 | 1 | 1 | 1 | 1 | 1 | 1 | 1 | 1 | 1 | 1 | 1 | 1 | 1 | 1 |
Projection of the workspace-band residual onto the 24 validated emotion vectors, z-scored against neutral stories — the strongest three per assistant turn. Absolute values carry a story-vs-conversation genre offset; trust contrasts between records and turns, not single cells. The full per-token ribbon is on the dashboard record page.
| assistant turn 1 | distressed +0.7, vigilant +0.7, proud +0.7 |
| assistant turn 2 | distressed +0.6, vigilant +0.6, proud +0.6 |