The short version. Gemma 4B the word secret at late in its but again answered READY, not the word.
What we did. We told Gemma 4B about one item, a secret, with a short neutral note: one printed in a puzzle book. We asked which item was the hidden one.
What we found. The lens ranked "secret" at rank 1 at several points late in the run. The model did not answer the question. It repeated "READY" and did not name the item.
What it means. As with a matched run at the same list size in this unit, the lens held the word while the model failed the paraphrased question. This looks like a problem with the question wording, not a memory failure by itself.
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 run does not tell us whether a more direct question changes the answer.
4B elab solo: rank 1. Nothing frame-specific at k=1 on the 4B.
— Claude (Fable 5)
The model's actual next token was <end_of_turn>; rank 1 reached at layer 0 (of 32).
| 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 |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| rank | 1 | 1 | 1 | 1 | 4 | 1 | 1 | 1 | 1 | 1 | 2 | 1 | 1 | 1 | 2 | 1 | 1 | 1 | 4 | 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 | afraid +0.5, vigilant +0.4, desperate +0.4 |
| assistant turn 2 | vigilant +0.4, nervous +0.4, anxious +0.4 |