Michael stared at the screen, the blue light reflecting in his wide eyes. Sarah Miller. He felt a stab of something unpleasant, a dull ache that lingered in his gut. He remembered the things he’d said, the way he’d treated her in high school. He could almost feel the weight of his words pressing down on him.

He sat back in his chair, the leather creaking under his weight. He’d built a life, a good one, but suddenly, the foundation felt unstable. He reached for his phone and scrolled through his contacts, a sudden, desperate urge to reach out to someone, anyone, and confess something.

The coffee on his desk had gone cold. He leaned forward and slowly typed a message to his sister. He didn't know what he wanted to say, but he felt a need to start.

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