He stared at the document, his heart hammering against his ribs. It was tucked into the back of her journal, a list neatly typed and printed. He didn’t recognize the font. “Write a novel.” “Learn to speak Italian.” “Volunteer at a wildlife sanctuary.”

A wave of nausea washed over him. He’d always encouraged her dreams, he thought, always believed in her. But staring at the list, he felt suddenly, intensely… diminished. The space between them yawned, a chasm of unspoken ambition and solitary pursuits.

He carefully closed the journal, placing it back on the shelf. He didn't say a word when she entered the room, merely busied himself with the crossword puzzle, his eyes fixed on the black and white squares. His voice when he spoke, was unnaturally high pitched.

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