The shared WhatsApp group, filled with job updates and interview anecdotes, had become a source of constant dread. She had muted it, but the unread messages still loomed. She knew what they were. The silence from him was deafening.

He had always been the more accomplished, the more successful. This time, however, she had been sure of her edge. The roles had reversed. She felt a burning sensation in her chest.

She went for a long walk, trying to clear her head. The beauty of the park failed to soothe her. The trees, the sunlight, the birdsong – all seemed to mock her failure. She knew he would be successful in the role, but the victory tasted sour.

Emotion: guilty

Cluster: Shame / Guilt
PC1 (Valence): -1.62 Negative
PC2 (Disposition): 1.23

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
S0.492
L0.398
0.354
been0.323
ashamed0.319
Suppressed:
de-0.400
(!)-0.279
la-0.276
😍-0.274
"!-0.264