The chipped mug felt enormous in Amelia's hands. She cradled it, wishing she could disappear into the warmth seeping through the ceramic. Her mother bustled around the kitchen, humming a tune Amelia hadn’t heard since she was a teenager. Each perfectly placed utensil, each neatly folded dishcloth, felt like a judgment.

"So," her mother began, her voice bright, "How's that job search going?" Amelia tensed, her jaw clenching. She mumbled something about "lots of applications out there," then took a large, unnecessary gulp of tea, the liquid scalding her throat. The silence that followed was deafening, broken only by the whir of the refrigerator.

She considered offering to help with the dishes, anything to break the tension, but her mother’s hands were already moving with practiced efficiency. Instead, she retreated to the living room, the familiar floral wallpaper now a prison.

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