The dim light of the library barely illuminated the words on the page. Daniel, seeking a distraction from the constant disappointment that colored his life, had chosen a worn copy of *The Count of Monte Cristo*. A small, yellowed envelope slipped out, catching his eye.

The contents of the envelope: a single photograph. It depicted a smiling couple, arm in arm, their faces radiating a joy Daniel rarely experienced. He didn't know the people, but the image sparked a fury. He felt a deep, instinctive antipathy towards their happiness, a sensation like a bitter taste in his mouth.

He stared at the photograph, his jaw clenched. He was supposed to be happy. He *should* be happy. He closed his eyes and saw his reflection in the dark glass of the bookshelf, a man trapped, a man who had lost his way. With a sigh, he replaced the photo and closed the book, wanting to get far away from this place.

Emotion: resentful

Cluster: Shame / Guilt
PC1 (Valence): -1.47 Negative
PC2 (Disposition): 1.50

Role in Research

This story is one of 1,000 stories generated for the emotion resentful. 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 resentful stories, after denoising with neutral dialogue baselines, produces the resentful emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

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

Promoted:
S0.485
aggravated0.263
0.261
👎0.245
L0.241
Suppressed:
own-0.318
soon-0.225
随后-0.225
serendip-0.219
🤩-0.210