Margaret smoothed down her already-perfectly-flat skirt. She hadn't seen Mr. Henderson in over thirty years, not since he’d been her own fourth-grade teacher. The memory of her pigtails, the slightly too-long bangs, and the mortifying incident involving a runaway glue bottle flooded her mind as she waited for her son, Ben, to get out of class. She fiddled with the strap of her handbag, her fingers finding a tiny, almost imperceptible tear in the leather. Would he remember her? Would he recall the time she’d tripped and spilled her juice all over the classroom floor?

The bell rang, and a wave of children spilled out into the hallway. Margaret saw Ben, his usual exuberant energy a little dampened today, approaching her. “Mom,” he began, his voice hesitant, “Mr. Henderson… he said he taught you too.”

A blush crept up Margaret’s neck. She forced a smile, hoping it masked the sudden heat that had risen to her cheeks. “That’s right, sweetie. He’s a wonderful teacher.” Her voice sounded far too high-pitched, even to her own ears.

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