The email sat in her inbox, unread for nearly an hour. She knew what it contained. Professor Davies' goodbye announcement had been circulating amongst the graduate students all morning. Her own fingers trembled as she finally clicked it open. He was leaving for a position at a prestigious think tank, a promotion she'd known was coming. But a coldness spread through her chest as she scrolled down to the brief personal message, a mere afterthought in his formal farewell. Sheโ€™d wasted so much time, so much of *his* time.

He had always been so encouraging. Now, she felt a profound heaviness, a reluctance to look him in the eye during their next meeting. The weight of her unfinished draft, the endless revisions that sheโ€™d never quite delivered, seemed to press down on her. The silence in the library felt thick, suffocating. She closed the laptop, a decision. She would not face him.

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
้€ƒ0.297
๐Ÿ˜ž0.295
Suppressed:
de-0.539
que-0.300
๐Ÿ˜-0.288
(!)-0.269
๐Ÿคฉ-0.242