The sun beat down mercilessly, but inside the old shed was still cold and damp. She shivered, pulling her jacket tighter. The task felt overwhelming, a seemingly endless parade of memories. She always hated this place.

The letter. Her father’s draft resignation from a job he had loved. The typed words, the apologetic tone, the sense of failure – it was all so unexpected. He was always so confident, so assured.

She felt a hot flush rise in her cheeks. Her own recent struggles felt amplified, magnified. Her own doubts seemed less personal, more something shared. She needed to get out of here, away from these ghosts and this oppressive sense of scrutiny.

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