Michael slammed his textbook shut. The words swam before his eyes, blurring with a sudden rush of heat. He felt a throbbing pulse behind his eyelids. The college, once a vibrant hub of possibility, was now a sinking ship. He'd bragged about his acceptance, about the prestige, to his friends. How would he face them now?

He hunched his shoulders and ducked his head as he passed a group of students in the quad. He wanted to be invisible. He felt as if their laughter was aimed at him, their whispers carrying the weight of his failing.

That night, he avoided the family dinner, feigning illness. He stayed in his room, staring at the ceiling, the unspoken accusations of his parents' disappointment hanging heavy in the air.

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