The tiny, cramped apartment felt like it was closing in on Leo. He knew he shouldn't be snooping, but the list, scrawled in Maya's familiar handwriting, practically glowed under the dim overhead light of the kitchen. "Learn to Surf," it declared boldly. Leo shifted his weight, suddenly acutely aware of the slightly too-tight jeans he was wearing. He ran a hand through his already messy hair, feeling a prickle of unease.

He hated the ocean. The waves, the sand, the whole atmosphere of carefree fun felt utterly alien to him. He imagined himself, awkwardly stumbling on a board while Maya, effortlessly graceful, rode the crests with a dazzling smile. The image tightened his chest.

He should just put it back, pretend he hadn't seen it. He felt the familiar heat creeping up his neck. He quickly scanned the rest of the list. "Visit the Amazon Rainforest." "Write a Novel." The weight of his own unfulfilled ambitions settled heavily in his stomach. He wasn't even sure he was good enough to be her boyfriend, and now this.

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