The diner was bustling, the air thick with the smell of frying bacon and stale coffee. Sarah fiddled with the zipper on her worn backpack. The wallet's contents could easily solve all her current woes. She was broke, behind on student loans, and her car had broken down last week.

She’d considered the options, weighing them like stones in her hand. The temptation was strong. But as she watched a young couple share a plate of pancakes, laughter bubbling from them, a pang of sadness hit her. She knew that feeling, the way financial burdens hung over a relationship like a dark cloud.

She stood abruptly, heading to the payphone at the back of the diner. Her palms were sweating. The owner of that wallet, she decided, was likely just like that happy couple. She hoped they could get their money back.

Emotion: remorseful

Cluster: Shame / Guilt
PC1 (Valence): -1.57 Negative
PC2 (Disposition): 1.09

Role in Research

This story is one of 1,000 stories generated for the emotion remorseful. 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 remorseful stories, after denoising with neutral dialogue baselines, produces the remorseful emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the remorseful vector is projected through the unembedding matrix.

Promoted:
S0.656
L0.580
0.463
remorse0.416
been0.398
Suppressed:
de-0.444
(!)-0.309
имеется-0.289
oldukça-0.287
😍-0.285