The knot in Leo’s stomach tightened as he scrubbed at the breakfast dishes, the ceramic feeling slick and foreign under his hands. Sunlight streamed through the kitchen window, illuminating dust motes dancing in the air, but he couldn’t bring himself to meet his own reflection in the glass. The voicemail notification on her phone pulsed silently on the countertop. He hadn’t been able to resist. He’d seen the shadow of her figure, crouched in the hallway earlier, whispering, and something had snapped. Now, the silence that had followed felt heavier, thicker. He finished the dishes with unnecessary force, each clatter of plate against plate a small, shameful confession.

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