"Did you hear?" The question came from across the cubicle farm, a breezy, cheerful tone. John flinched. He should have known. The news would be everywhere. He forced a smile and offered a curt nod, his gaze fixed on his screen. He felt a tight band around his chest.

He avoided his colleague's gaze for the rest of the afternoon. He ate lunch alone, his appetite gone. He replayed every interaction, every presentation, every email he'd sent, searching for clues to what he'd done wrong. The feeling of being exposed and lacking.

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