The shadows in the living room seemed to deepen, amplifying the silence. She’d been such a fool. She'd vetoed the idea of a dog, a golden retriever, because she’d convinced herself it was too much responsibility. Now, staring at the empty dog bed she saw in a store window, she felt a profound sense of anguish.

He, Mark, had wanted a dog so badly. She knew she'd hurt him. She remembered the way his face had fallen, the way his shoulders had slumped. Now, alone in the apartment, the absence of his usual banter weighed on her.

She picked up her phone, scrolling through pictures of golden retrievers. Each image was a fresh stab of guilt. She’d been overly practical, focused on the potential inconvenience, and in doing so, had denied them both something wonderful.

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