The listing popped up while she was supposed to be working. A picture of the familiar brick facade, the overgrown rose bush she’d been tasked with pruning every summer – a task she’d always loathed, which now felt like a punch to the gut. She clicked the link, her heart rate spiking. Each photo was a slow burn of memory and judgment. The living room, bathed in too much sunlight, highlighted every imperfection in the worn rug. She remembered her mother meticulously cleaning it before guests arrived, and she immediately felt a flush creep up her neck.

She scrolled through the kitchen, taking in the granite countertops, the stainless-steel appliances. Not the same chipped Formica she remembered. She imagined strangers walking through that kitchen, judging her family's choices, judging *her*. She slammed her laptop shut. This was a terrible idea.

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