A wave of dizziness washed over Sarah as she read the email. The subject line, “Plagiarism Allegation,” seemed to vibrate in her hand. She pressed her fingers against her temples, trying to ward off the building headache. She’d been living on coffee and adrenaline for weeks, trying to balance her demanding coursework with her part-time job.

She felt a profound sense of disillusionment, as if the very foundations of her academic aspirations had been shaken. She stared out of the window at the rain, the droplets blurring her vision.

The weight of the accusations felt unbearable, a physical pressure that squeezed the air from her lungs. She wanted to run, to escape the crushing weight of it all.

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