He avoided the department head’s office all day. The door, usually so innocuous, now seemed to leer at him. He pictured the conversation, the awkward pleasantries, the inevitable questions about his progress. He'd been stringing his advisor along for months, feigning enthusiasm for a project he’d secretly abandoned. He knew it showed in his work, the sparse research notes, the meandering prose.

He found himself lingering in the coffee shop, nursing a lukewarm Americano. Each sip was a reminder of the money wasted, the resources squandered. His chest tightened. Why couldn’t he have just been honest? He felt a deep, uncomfortable pressure in his gut whenever he thought about the topic. The faces of his colleagues, usually familiar and friendly, seemed to shift, to subtly judge.

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