David stared at the crumpled takeout menu in his hand, the Chinese characters staring back at him like mocking eyes. He’d been so careful. Weeks he’d spent avoiding conversations in Mandarin, deflecting his wife, Mei’s, questions about his day. The careful construction of his English, even around his closest friend, felt like a flimsy shield. Now, he heard it - the rhythmic cadence, the rise and fall of tones, issuing from the kitchen. Mei was cooking, presumably, a dish he could no longer pretend not to recognise. He felt heat crawl up his neck.

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