The scent of roasting coffee filled the air, mingling with the unfamiliar sound of Hindi. It was coming from the living room, where Leo usually spent his mornings reading. He’d assumed Leo was working. But the phrases he heard were more than just isolated words. It was a conversation, a deliberate effort to understand. Sarah felt her face burn. She’d deliberately neglected her heritage, found it too cumbersome, too different. She didn’t know how to face him, the man who had effortlessly embraced what she had rejected. She needed to be alone.

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