The short version. Gemma 12B the word "shame" at throughout the run and named it correctly when asked.
What we did. We told Gemma 12B about one item, the word "shame", with a short neutral note: a word from an etiquette manual. We asked which item was the disgrace.
What we found. The ranked the tracked word at rank 1 at every point we checked late in the run. The model named it correctly.
What it means. This matches the other single-word floor runs in this unit. A short neutral note did not change how well one word alone holds.
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. One word alone does not test several words held together.
12B elab solo: rank 1, indistinguishable from self/flat solos.
— 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 | 2 | 2 | 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 | vigilant +0.8, distressed +0.8, nervous +0.7 |
| assistant turn 2 | proud +0.4, afraid +0.4, curious +0.3 |