She stared at the open laptop, the glowing screen reflecting in her tired eyes. The headline screamed: "The Undying Grit of Clara Bellweather." Clara had not been consulted. Each paragraph felt like a violation, detailing her every setback, every triumph, every single doubt. A headache hammered at the base of her skull. She sat hunched in her chair, a posture she recognized as her default these days.

Her fingers trembled as she scrolled, the words blurring before her. The author had interviewed her childhood friends, her ex-boyfriends, even her estranged mother. Details she’d worked to bury, meticulously, were now splashed across the internet for anyone to see. She closed the laptop, the sudden darkness a physical relief.

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