The harsh fluorescent lights of the storage unit felt colder than the November air outside. Daniel watched his sister, Chloe, meticulously cataloging the contents of the safe deposit box. A collection of priceless jewels. She seemed as if she belonged.

Daniel, on the other hand, felt a wave of dizziness wash over him. He was barely able to stand up. He’d expected something, anything, but not the contents of the battered old suitcase the solicitor had entrusted to him.

Inside, a collection of his father’s old tools. His father had been a skilled craftsman. Daniel, the accountant, knew nothing about any of this. He was useless.

He wanted to run. He felt a burning in his chest and his palms were slick with sweat. He should have known better. He was just a failure.

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