The humidity was suffocating, clinging to Daniel’s skin like a shroud. He felt as though he could barely draw breath, the air thick and heavy. The relentless demands of the day had left him feeling hollow. He wanted the world to stop; he longed for the peace of silence. He felt as if his very muscles were heavy.

He shuffled through the maze of tables, his eyes glazed over. Then, he saw it. A flash of familiar brown. His childhood teddy bear. He froze, a strange mix of emotions washing over him.

He reached out, his hand trembling slightly. The seller, a wizened old man, quoted a price. Daniel paid, his movements slow and deliberate. He wanted to sit down, to close his eyes, to simply... be. He needed a moment to recover.

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