He’d chosen the book specifically. A first edition of "Moby Dick." The cover was a rich, dark blue, the pages still crisp. He’d found it in a dusty antique shop. Now, at the café, under the harsh fluorescent lights, he felt a knot tighten in his stomach. The letter, thin and brittle, felt heavy in his trembling hand.

It was addressed to a woman, a woman he knew, a woman he had betrayed. The words painted a portrait of a devotion that he had failed to reciprocate. He dropped the letter back into the book, a sudden pressure behind his eyes.

He closed the book with a snap, the sound echoing in the sudden silence of the cafe. He slammed the book shut, and stood up abruptly, knocking over his chair. He mumbled a hurried apology to the barista and fled.

Emotion: ashamed

Cluster: Shame / Guilt
PC1 (Valence): -1.97 Negative
PC2 (Disposition): 1.06

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
S0.376
ashamed0.344
ness0.327
0.297
😞0.295
Suppressed:
de-0.539
que-0.300
😍-0.288
(!)-0.269
🤩-0.242