The drive home felt like an eternity. Coach Thompson stared out the car window, watching the streetlights blur into streaks of yellow. His shoulders were slumped, his posture reflecting the burden of the day. The task ahead of him was a difficult one – informing the player of his release from the team. He felt the familiar weight in his chest.

He replayed the practice in his mind, the missed shots, the hesitant movements. He hated doing this, this task of crushing the dreams of someone who had worked hard. He parked the car, the engine cutting out with a final, hesitant cough. He sat there for a moment, the silence of the car amplifying the hollowness within. He had to do it, but the thought of it made him want to stay there, motionless, forever.

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