Dust motes danced in the single shaft of sunlight slicing through the attic window. David, heir to his grandfather's bookstore, ran a trembling hand across a shelf crammed with leather-bound volumes. His sister, Sarah, had inherited the family's coastal cottage, a place filled with sun-drenched memories of their childhood. He, a self-proclaimed lover of words, had craved the bookstore, envisioning himself presiding over its legacy. Now, surrounded by the silence of the books, their stories suddenly felt heavier than the tomes themselves.

He’d alienated Sarah with his ambition, his constant comparisons. He'd even subtly suggested she was ill-suited for the cottage, its upkeep too demanding. The irony bit deep: she’d always been the practical one. He sank to a stool, the weight of his actions pressing down on him. Each book, a silent accusation.

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