"Looking for anything in particular?" The woman running the sale had a friendly smile, but it felt like a spotlight on Leo. He stammered, his cheeks burning. “Just… browsing.”

He was almost at the end of the row when he saw it. It was an old, moth-eaten teddy bear. He recognized the crooked stitch on one ear. He felt a lump form in his throat.

He knelt down, the gravel digging into his knees. He ran a finger across the worn fur, memories flooding back. He heard the woman's footsteps approaching. He blurted out, "How much?" his voice cracking. He hated how eager he sounded, how vulnerable. He averted his gaze as the woman named a price.

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