Clara stared at the list, the elegant script of Liam’s writing mocking her. “Learn to Code” was top of the list. She bit her lip, a nervous habit she’d been trying to break. Liam, a software engineer, possessed a world of knowledge she could only dream of understanding. She felt like a small child standing next to a towering skyscraper.

He’d always been so supportive of her art, her paintings that she made in her spare time. Yet now this new aspiration of his, so clever, so…technical. She instinctively curled her toes inside her socks.

She reread the second point on the list: "Climb Mount Kilimanjaro." Her breath hitched. She could barely manage a brisk walk around the park without feeling winded. The contrast between his adventurous spirit and her own quiet life suddenly felt cavernous. She felt a flush rising to her cheeks.

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