A lead weight seemed to have taken residence in Mark's chest. Even breathing was an effort. He stared out the window, the traffic below seeming to hum and drone. The prospect of starting his workday filled him with a sense of dread.

He dragged himself into the office, the usual bustle and chatter grating on his nerves. He found himself avoiding eye contact, preferring the isolation of his cubicle. The fluorescent lights above felt like a physical threat.

Later that week, at a medical conference, a specialist presented a case study. The patient's symptoms were eerily familiar. The doctor mentioned an identical case, a woman from his own town. Hope flickered, a tiny ember in the vast darkness.

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
à°­à°¿-0.214