The brightly lit arcade felt overwhelming. Noise, flashing lights, the smell of pizza – it was sensory overload. He'd envisioned a cool, laid-back hangout for his birthday. Instead, Liam's bowling party across town seemed to have drawn everyone, including all the girls he liked.

He hunched his shoulders, awkwardly maneuvering through the crowd. He kept looking down at his shoes, avoiding eye contact. He knew he'd fumble when he played the claw machine. He’d probably lose at air hockey.

The few friends who came were clearly already looking at their phones, itching to leave, too. He felt the familiar sinking feeling of inadequacy.

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