The drive back from the grocery store had been a struggle, each traffic light an obstacle, each turn a challenge. Michael finally parked the car, the engine dying with a final, shuddering gasp. The weight of the bags, usually manageable, felt insurmountable. He saw the letter when he opened the mailbox. It was a worn, folded page, penned by his own hand years ago, addressed to his first love. He leaned against the car, the metal cool against his skin.

“I feel lost,” the letter began.

The words echoed in the sudden silence. He could almost feel the youthful despair, the angst that had driven the letter's creation. He thought about the past. He thought about his future. He sighed.

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