The diner was bustling with Saturday morning activity, the clatter of plates and the murmur of conversations a deafening backdrop to John’s inner turmoil. Across the table, Michael sipped his coffee, his gaze distant. "I'm drawing a blank, I'm afraid," Michael said, shaking his head.

John’s carefully chosen words – a quote from a book they’d both loved as kids – hung in the air, heavy and useless. He’d envisioned a shared smile, a flash of recognition. Instead, the waiter, who had come over to check on them, looked at him with an inquiring glance. John felt the blood rush to his head. He pushed his plate away, suddenly unable to eat. The aroma of bacon and eggs turned his stomach. He’d come all this way for nothing.

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