The movie theater was dimly lit, the credits rolling across the screen. He knew this movie meant a lot to her. Ben fidgeted in his seat. He should have known. He had dismissed her love for the classic movies as childish and unrealistic online. Now, he watched her profile in the dim light.

He'd been callous, he realized, and the weight of his actions pressed down on him. Seeing her here, and knowing that he had hurt her, was something he couldn't get over. She looked at him.

He wanted to reach out, to say something, anything. But the words were trapped, lost somewhere in the darkness between them. He sat in his chair, completely frozen.

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