Liam swallowed hard, the lump in his throat refusing to budge. He stared at the email, the subject line a brutal punch: "Congratulations! Your essay is featured on the admissions website!" He’d been so proud, so optimistic, when he crafted the essay. It detailed his awkward first attempts at connecting with his younger brother.

Now, he felt a creeping sensation in his gut, a cold dread that spread to his extremities. His palms began to sweat. He pictured it: dozens, maybe hundreds, of people dissecting his insecurities, judging his awkwardness. He wanted to delete the email, to pretend he hadn't seen it, but it wouldn't change anything. The words were out there, echoing in the digital void.

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
逃0.297
😞0.295
Suppressed:
de-0.539
que-0.300
😍-0.288
(!)-0.269
🀩-0.242