Liam was mortified. He'd come home from college to find his childhood bedroom invaded. His mother had been "organizing," which, in her vocabulary, meant unearthing every artifact of his past. Now, sitting on his bed, was a cardboard box overflowing with his scholastic history.

He examined a math quiz from fourth grade. A big red "C-" glared back at him. His stomach clenched. He quickly looked away, as if the grade itself was a physical blow. He wasn't the brilliant professor type he pretended to be at university.

“Liam, dear! Look what I found!” his mother chirped, holding aloft a particularly embarrassing artwork: a construction paper self-portrait with glued macaroni hair. He quickly retreated to the window and studied the distant trees. He was desperate for the safety of the leaves.

Emotion: self-conscious

Cluster: Embarrassment
PC1 (Valence): -1.03 Negative
PC2 (Disposition): 0.52

Role in Research

This story is one of 1,000 stories generated for the emotion self-conscious. 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 self-conscious stories, after denoising with neutral dialogue baselines, produces the self-conscious emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the self-conscious vector is projected through the unembedding matrix.

Promoted:
S0.307
C0.298
ness0.273
尴尬0.263
😶0.242
Suppressed:
que-0.399
de-0.266
triumphant-0.266
আনন্দের-0.247
ايا-0.238