A tremor ran through Sarah's hands as she sat across from the review board. The harsh fluorescent lights seemed to amplify the silence. Her carefully constructed facade of confidence crumbled as the professor began to outline the similarities between her essay and another published work. Her throat constricted, making it difficult to breathe, each word a tiny hammer blow against her already fragile composure.

She couldn’t meet their eyes, instead studying the intricate pattern on the worn mahogany table, tracing the wood grain with a trembling finger. The air grew heavy, pressing down on her shoulders.

"Did you...?" the professor began, his voice softening with concern, but the question hung unfinished. Sarah simply shook her head, unable to find the words to defend herself. A hot flush crept up her neck, staining her cheeks.

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