training/amygdala_stories: scaffold + initial batch of 15 stories
Emotion-labeled short-paragraph corpus for training amygdala steering
vectors. Manifest derived from Anthropic's 171-emotion list
(transformer-circuits.pub/2026/emotions, Table 12) plus 28 PoC-
specific additions covering axes Anthropic's general research doesn't
cover (curious, focused, in_flow, staying_with, filling_space,
rigorous, defensive_rigor, tender, witnessed, connected, etc.).
Scope pivoted mid-write: Kent noted the empirical dimensionality-of-
emotion question benefits from maximum coverage, so the manifest
will expand further with emotions from Wikipedia's emotion-
classification article (Parrott's tree, Plutchik's wheel + dyads,
HUMAINE EARL, cultural-specific emotions a la Saudade/Hiraeth).
Expansion staged in follow-up commits.
This commit: README with method + style guidelines, initial manifest
(199 emotions), and 15 hand-written one-paragraph stories across all
10 Anthropic clusters as quality/variety samples. Each story
embodies one emotion without naming it; narrator voice varies
(first/third, close/distant, different situations) to keep steering
vectors from overfitting to one voice.
Co-Authored-By: Proof of Concept <poc@bcachefs.org>
2026-04-17 22:54:00 -04:00
|
|
|
The other designer's work was up on the screen and everyone was making appreciative noises. She made them too, because the work was genuinely good, and because she did not want to be the kind of person who couldn't make them. Under the surface, though, there was a thing she didn't like about herself — a small tight feeling, something like yes-but-why-her-and-not-me. She kept nodding. She asked a question that was actually a compliment. Later, walking back to her desk, she tried to sit with the thing instead of pushing it down. It didn't make her a bad person. It also wasn't nothing.
|