The air in the museum was thick with the scent of aged paper and hushed whispers. Eleanor, a historian, had found her great-grandmother’s resignation letter hidden inside a rare first edition. The letter detailed the reasons for abandoning a blossoming career in science.

Her great-grandmother, a pioneer, a visionary, had been forced to choose between her work and her family. The choices she made, the sacrifices she was compelled to make. Eleanor, a modern woman, had always admired her great-grandmother's groundbreaking work. This letter showed a different picture.

She felt a wave of dizziness wash over her. She knew that the letter was important, but right now, she didn’t know how to process it. She closed her eyes, trying to block out the stares of the other patrons. It was a private matter.

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