The book lay open on the kitchen counter, its cover a garish collage of his face superimposed on a football. He hadn’t known. He hadn't consented. A wave of heat flushed his cheeks as he scanned the first paragraph, the writer detailing his childhood penchant for breaking things. He slammed the book shut, the sound echoing in the sudden silence. He went to the sink, splashing cold water on his face, trying to cool the burn. He couldn't meet his reflection's gaze.

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