The first day back after summer always felt the worst, thought Mr. Davies. He knew the students would be studying his every move, ready to judge and criticize everything. He hated the scrutiny. He wanted to run back home and hide under the covers.

As he walked into the teachers’ lounge, he saw a small, oddly shaped package on his usual chair. He froze, his pulse quickening. He wasn't sure he could open it.

He sat down, slowly, and picked it up. It was wrapped in brown paper, tied with twine. He untied the knot, his fingers clumsy.

Inside the package was a handmade wooden birdhouse, meticulously carved and painted. A tiny note read, “Thank you for helping me find my voice." It was from David, a student with a severe stutter who'd spent most of his time looking down at his desk. A smile, a real one, crept across his face.

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