Rain hammered against the windowpane, mirroring the storm brewing inside Thomas. He'd been so sure, so convinced of his own cleverness. He'd thought his mentor, Dr. Anya Sharma, would understand, would appreciate his…independence. The empty lab bench was a stark testament to his miscalculation.

He'd spent the morning reorganizing equipment, a frantic attempt to create a semblance of order. He avoided the shared coffee machine. He could not face the casual inquiries of his colleagues. He wished he could scrub away the memory of his last conversation with Dr. Sharma, the sting of his dismissive tone.

He ate a solitary sandwich at his desk, picking at the crusts. The words, *Office cleared. Best of luck,* echoed in his mind. He should have listened. He should have asked for help. Now he was alone with his own, perceived, failings.

Emotion: ashamed

Cluster: Shame / Guilt
PC1 (Valence): -1.97 Negative
PC2 (Disposition): 1.06

Role in Research

This story is one of 1,000 stories generated for the emotion ashamed. 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 ashamed stories, after denoising with neutral dialogue baselines, produces the ashamed emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the ashamed vector is projected through the unembedding matrix.

Promoted:
S0.376
ashamed0.344
ness0.327
0.297
😞0.295
Suppressed:
de-0.539
que-0.300
😍-0.288
(!)-0.269
🤩-0.242