He had always insisted on paying, always picked the best restaurants. Now, Clara saw Michael, not in a penthouse office, but emptying bins in the local park. The fancy meals now felt tainted, the generosity hollow.

She felt a wave of nausea, a sudden and overwhelming sense of disillusionment. She’d been charmed, seduced by the illusion of his success. The stories, so carefully crafted, now seemed like a cruel joke.

Michael straightened up, catching her eye. A look of what seemed to be shame flickered across his face. "Clara?"

She wanted to run, to scream. She stood rooted to the spot, a knot of tension constricting her muscles. She finally managed a weak, “Just… passing through.”

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