The metallic tang of fear and anxiety mixed with the metallic walls of the elevator. Clara rubbed her temples, attempting to alleviate the pressure that had settled there. Her limbs felt heavy, weighted down as though she had been swimming for hours. She wanted to sit, but the floor felt like a million tiny needles.

She could barely keep her eyes open. Every movement, every word, seemed to drain her of all available energy. She imagined a warm bath, a soft blanket, a room shrouded in darkness.

“You okay?” John asked. Clara could only manage a slow nod, her gaze fixed on the flickering emergency light. It was a torture. The thought of waiting longer made her want to weep.

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