The phone rang, and Leo flinched. It was probably Mrs. Petrov. He let the machine pick up. Her voice, thin and strained, filled the small apartment. "Leo, dear, I just… well, I saw the tree. It’s… a mess."

He'd known, of course. He’d seen the precarious lean of the willow for months, ignored the way its roots were buckling the pavement. He’d been too busy, too preoccupied with his own petty dramas.

He rubbed his temples. The headache had been persistent all morning. Now, it throbbed in time with the image of Mrs. Petrov standing in her garden, shoulders slumped, amongst the debris. He hated the way his stomach twisted.

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