The coffee tasted like dirt, but Maya forced herself to drink it anyway. She had been subsisting on caffeine and instant noodles for weeks. Dr. Olsen’s office was a beacon of order in the chaos of the university, and a place where she had found some small amount of confidence. And now, she found out, that beacon was dimming. An email notified her of his move to another school, a new, better position.

She pushed her plate around, barely touching her food. The thought of finding a new advisor, of explaining her research all over again, filled her with a profound sense of inertia.

She closed her eyes and the exhaustion settled in, a heavy fog.

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