The city noise, usually a comforting backdrop, felt like a cacophony. He had taken the rejection letter, crumpled it, and thrown it in the bin. He'd spent the day wandering, the aimless movement failing to provide any solace. He felt a deep, profound void, an emptiness that seemed to swallow everything.

He sat on a park bench, the cold metal seeping through his jeans. He watched the world go by – couples laughing, children playing, people rushing home – and felt utterly disconnected. He barely registered their existence. His eyelids drooped, and a profound lethargy settled over him, threatening to engulf him in darkness. He wished the sun would set and he could find his own internal stillness.

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