The air in the breakroom, usually a welcome reprieve, felt stale and stagnant. Henry sat there, leaning against the vending machine. The email was still in his inbox: *New Employee Onboarding: Henry to train Robert*.

Robert, standing beside him, was talking. Henry barely heard what he was saying. He could feel the blood pulsing in his temples.

He could feel the pull to simply lie down. He made a vague gesture. He said, “That’s, you know, it’s like that,” barely audible. He wanted to go home. The idea of going back to his desk was… taxing.

Emotion: tired

Cluster: Fatigue / Lethargy
PC1 (Valence): -0.92 Negative
PC2 (Disposition): -1.00

Role in Research

This story is one of 1,000 stories generated for the emotion tired. 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 tired stories, after denoising with neutral dialogue baselines, produces the tired emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the tired vector is projected through the unembedding matrix.

Promoted:
weary0.254
fatigue0.249
😴0.238
sighed0.237
barely0.230
Suppressed:
C-0.268
because-0.225
B-0.219
🤟-0.217
భి-0.214