The university cafeteria buzzed with a noisy energy that grated on Sarah's nerves. She’d received a shockingly low score on her music theory midterm, and the melody of celebratory chatter felt like a discordant symphony. Her coffee cup trembled in her hands. She hadn’t been able to concentrate, her thoughts always circling back to the test. She skipped dinner the night before and felt weak.

She took a shaky breath, the aroma of the brewing coffee doing little to settle her nerves. The bright sunlight streamed through the windows, making her head throb. She wished she was anywhere else.

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