A wave of sluggishness washed over Mark as he reviewed the printout. He’d been expecting a simple check-up, perhaps some bloodwork. Instead, he was staring at a document detailing a complex condition he’d never experienced. His shoulders sagged.

“Are you sure this is correct?” he asked, his voice a low, gravelly whisper. The nurse’s face was a mask of professional concern.

She studied the chart intently, then her eyebrows furrowed. "Let me double-check," she said, before scurrying away. He rubbed his temples, a dull ache throbbing behind his eyes. The room seemed to be spinning slightly. He just wanted to go home and lie down.

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