The moment the announcement came over the PA system, David's stomach turned. He'd poured his heart into this job, always the first in, last to leave. He’d meticulously crafted his presentation, the one that he believed would clinch the deal. The winning candidate: Emily. He imagined her, already settling into the corner office, while he… well, he'd be here. Again.

He avoided the water cooler, the communal area, the places where congratulatory handshakes and forced smiles would be waiting. He slipped into the supply closet and leaned against the cold metal shelving. He felt his face flush. He needed a moment. After a while, he went back to his desk, but kept his head down, hoping to remain unnoticed.

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
逃0.297
😞0.295
Suppressed:
de-0.539
que-0.300
😍-0.288
(!)-0.269
🀩-0.242