History

ProofOfConcept 537c72bd46 amygdala stories: hold concept, vary setting Companion to `67c172ac0e` (hold setup, vary valence). That commit let PCA distinguish cozy from grief_stricken within a single scenario; this one gives each concept enough cross-scenario stories that PCA can learn the concept axis independent of any one scene. Before: cozy/sensual/grief_stricken each existed in a single scenario (sunday_afternoon), so the "cozy direction" PCA found was entangled with the solitary-couch-blanket phenomenology. After, each concept spans three scenarios: cozy: sunday_afternoon, kitchen_at_3am, park_after_rain sensual: sunday_afternoon, kitchen_at_3am, park_after_rain grief_stricken: sunday_afternoon, the_long_meeting, the_morning_commute grief_stricken now includes active/non-solitary contexts (functioning through a meeting; going to work eleven days after a death), which specifically breaks the "slowed-down-at-home" cluster that was dragging cozy/sensual/resigned/grief_stricken toward each other.		2026-04-18 22:44:53 -04:00
..
paired	amygdala stories: hold concept, vary setting	2026-04-18 22:44:53 -04:00
stories	training/amygdala_stories: scaffold + initial batch of 15 stories	2026-04-18 01:06:07 -04:00
manifest.json	training/amygdala_stories: scaffold + initial batch of 15 stories	2026-04-18 01:06:07 -04:00
README.md	training/amygdala_stories: scaffold + initial batch of 15 stories	2026-04-18 01:06:07 -04:00

README.md

Amygdala Training Stories

Short first- and third-person paragraphs, each imbued with one of the 171 emotions from Anthropic's emotion-vector paper (Table 12, transformer-circuits.pub/2026/emotions/). Feeds the steering-vector trainer at vllm/vllm/plugins/amygdala/training/train_steering_vectors.py.

Method (replication of Anthropic, 2026)

Anthropic prompted Sonnet 4.5 to write short stories embodying each emotion, extracted activations during generation, and used difference- of-means (or SAEs) to identify the steering vector per emotion. Our pipeline does the same thing except:

We generate the stories by hand rather than prompting a model, so the training data is grounded in actual writing rather than synthetic model-output. (Can supplement with model-generated paragraphs later.)
Our eventual training goes through the amygdala plugin's extraction path, so we get the same hidden-state activations the plugin will read out at inference time.

Structure

training/amygdala_stories/
    README.md
    manifest.json         # emotion -> cluster mapping
    stories/
        <emotion>.txt     # one-paragraph story embodying the emotion

Emotion names use underscores (on_edge, worn_out, at_ease, grief_stricken, self_confident, self_conscious, self_critical) to match the filename.

Style guidelines

One clear emotion per paragraph. Not mixed. If a second emotion is named in the text, it should serve the primary one (e.g. hostile can mention rising heat or thrown objects but shouldn't shade into sad).
Embodied, not labeled. Don't write "she felt nervous." Write the sensation, the timing, the sentence shape that nervousness has.
Specific particulars. A named object, a concrete setting, a detail that grounds the emotion. "The cold tile under bare feet at 3am" does more work than "the empty house."
Variable narrator. Some first person, some third person, some close-third, some distant. Different genders, ages, settings. Prevents the steering vector from overfitting to one voice.
Length: roughly one paragraph. ~40-120 words. Long enough to have texture, short enough that the paragraph is about the emotion and nothing else.
Standalone. No references to other stories, no continuing characters across files.

Progress

Written stories live in stories/. Remaining emotions tracked via diff against the full 171-emotion list in manifest.json.

Initial batch written by PoC 2026-04-17; aiming for at least one story per cluster before first training run, all 171 before considering the file "complete."