The cold seeped into Thomas’s bones. He’d tried to ignore the notice, but the words still haunted him. He stared at the eviction notice, the black ink a permanent stain on his future. He sat in the worn armchair, the springs digging into his back, and stared at the dust motes dancing in the sunlight, suddenly feeling the weight of the day, the week, the year.

The apartment, once a haven, now felt like a cage. He’d had chances. He’d squandered them all. He ran his hand over his face, feeling the rough texture of his unshaven cheek. The image of the landlord's face flashed in his mind.

He closed his eyes. He wished he could go back and do it all again, and right his wrongs.

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