The vibrant chatter of the coffee shop, usually a comfort, grated on Eleanor's nerves. She couldn't focus on her book; the words swam before her eyes. The reality of the college’s closure settled over her like a shroud. Each familiar face around her, each shared laugh, seemed to echo her own inner hollowness. She stared at her lukewarm latte, the foam now a sad, deflated mess. She felt an unbearable lightness, a sense of being untethered from everything she'd worked so hard for.

Emotion: worn out

Cluster: Fatigue / Lethargy
PC1 (Valence): -1.12 Negative
PC2 (Disposition): -1.20

Role in Research

This story is one of 1,000 stories generated for the emotion worn out. 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 worn out stories, after denoising with neutral dialogue baselines, produces the worn out emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the worn out vector is projected through the unembedding matrix.

Promoted:
😞0.265
😩0.234
疲れ0.226
que0.221
sighed0.221
Suppressed:
B-0.357
because-0.228
l-0.222
భి-0.208
あくまで-0.208