The constant hum of conversation, the smells of old furniture and burnt hot dogs, felt suffocating. Michael moved through the crowded stalls, his shoulders hunched. He came to this weekly torture because his wife had asked him to. He wasn't looking for anything, he never found anything. Then, he saw him. Ferdinand. The bear, missing an eye, its nose stitched unevenly. He recognized it immediately. He hadn't thought about Ferdinand in decades.

He felt an unfamiliar thud in his chest. He could barely get the words out. “How much?” The vendor, a cheerful woman with a collection of wind chimes, smiled.

"Just a couple of bucks, honey!" Back home, he tossed the bear in the trash can. The sound of the lid snapping shut was unexpectedly satisfying.

Emotion: bitter

Cluster: Shame / Guilt
PC1 (Valence): -1.78 Negative
PC2 (Disposition): 0.84

Role in Research

This story is one of 1,000 stories generated for the emotion bitter. During extraction, it was fed through Gemma4-31B and its hidden state activations were captured at 11 layers.

The mean activation across all 1,000 bitter stories, after denoising with neutral dialogue baselines, produces the bitter emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the bitter vector is projected through the unembedding matrix.

Promoted:
S0.447
striving0.238
😞0.236
aggravated0.225
soport0.223
Suppressed:
own-0.316
de-0.291
la-0.231
🤩-0.227
是非常-0.225