Michael fiddled with the strap of his messenger bag, the worn leather cool against his sweaty palms. He hated these gatherings, the forced nostalgia, the shared sorrow that felt oddly performative. His childhood home, reduced to a pile of rubble in his mind, was an intensely private space, not a spectacle. His younger sister, Sarah, was chattering animatedly to their mother about the “good old days,” their voices carrying on the breeze.

He stared at the blank space where the house had stood. He wanted to be anywhere else. A knot formed in his stomach, and he focused on the cracks in the pavement, counting them. Each one felt like a judgmental eye.

He’d almost tripped on the uneven ground as he’d walked towards the site. He really must be more coordinated. He wished he could just take off his glasses and wipe his face and somehow disappear.

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