He stared at the rejection letter, the crisp paper a stark contrast to the crumpled stack of bills on his desk. His jaw ached from clenching it, a familiar tightness that had become a constant companion. The overhead light buzzed, a high-pitched whine that grated on his nerves.

He ran a hand through his hair, finding it plastered to his forehead with sweat. Sleep had become a distant memory, replaced by a relentless cycle of studying, working, and the gnawing anxiety of his financial situation. His eyelids felt heavy, as if weighted down.

"Well," he muttered, his voice raspy. "Guess it's ramen for another semester." He picked up the letter again, the edges blurring in his vision. The words seemed to mock him, the polite phrasing a cruel façade.

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