The train rattled along, each bump a jarring reminder of how utterly drained Maya was. The insistent chatter of the other passengers was a dull roar in her ears. She stared at the worn leather of her bag, the mundane details of her life suddenly weighing heavily on her. A wave of nausea hit her as she noticed the man across the aisle wearing the exact same scarf she’d painstakingly knitted for her boyfriend. The woman next to him, laughing at something he'd said, was clutching the same dog-eared copy of “Pride and Prejudice” that *he* always carried.

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