The old photographs lay scattered across the kitchen table. My sister, Olivia, was chuckling, pointing at a picture of our grandmother in a ridiculous hat. I felt a lump forming in my throat. The faded blue jeans I wore felt like a costume.

Olivia started recounting childhood memories, laughing at all the jokes. I remained silent, feeling as if I was watching a movie of someone else's life.

She turned to me, her brow furrowed slightly. "What do you think, Liam? Remember that trip to the beach?"

I nodded slowly, searching for a single memory, any memory that wasn't overshadowed by the overwhelming sense of not belonging. I swallowed hard, unable to meet her gaze.

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