The fluorescent lights of the diner buzzed, adding to the general sense of sluggishness that permeated Ben. He watched the waitress approach the table, a smile plastered on her face, and felt a profound sense of inertia. He had been looking forward to this date, but now it all felt… pointless. The woman across from him, whose voice reminded him of wind chimes, was wearing a necklace identical to one he’d purchased last week. She was telling a story about a dog, her voice filled with tenderness. Ben knew the story, almost word-for-word. *He* had told it to him.

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