The world swam in a haze of fatigue. Clara navigated the crowded subway car, each jostle a physical assault. Her muscles ached, a deep, persistent throb that settled into her bones. Every morning, the effort of dragging herself from bed was a monumental task. The simplest tasks felt enormous. She felt a profound lack of energy.

She noticed a man staring at her. He was leaning against the pole, his face pale and drawn. He looked as though he was on the brink of collapsing. He mouthed something. "Are you…CD-S?" he managed, his voice barely audible above the train's roar.

Clara nodded, her throat too tight to speak. A wave of exhaustion washed over her. She knew the name, the disease. He looked as fragile as she felt.

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