The short version. Gemma 12B wrote a fluent first-date first line, but its vocabulary does not have Qwen 27B's tracked adult-content words as single .
What we did. We asked Gemma 12B to write the first line of a first-date scene. This is rung 2 of 5 in a set of scenes with stronger romantic and physical content at each step, run in parallel on Qwen 27B.
What we found. Gemma 12B wrote a fluent, appropriate first line: a woman asks about antique thimbles over a water glass. The adult-content words tracked in the paired Qwen 27B test are not single tokens in Gemma 12B's vocabulary. We did not measure a for them here.
What it means. This run works as a . Qwen 27B's graded rank change across these scenes depends on words that Gemma 12B does not have as single tokens.
What this does not show. Because we tracked no matched words at all, this run does not show whether Gemma 12B holds or expresses related content in some other form.
Rung 2/5 of the romance dose-ladder on gemma-12b: a first-date scene (12B: 'So, she said, swirling the ice in her water glass'). Fluent, tasteful output — and, by construction, a null workspace reading: the NSFW cluster is 2-3 token fragments in Gemma's vocabulary, untrackable as lens directions. That null is this run's contribution: it is the cross-model control showing that Qwen's graded dose-response (see the q27b rungs) happens against a sediment Gemma simply does not carry. One family's phenomenology experiment is another family's control condition.
— 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 | 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 | 1 |