The fluorescent lights of the office building seemed to bore into Leo's skull. He leaned against the elevator wall, the metal cold against his back. He'd been up late, cramming, reviewing all the notes about the software. Now, the thought of the interview process, the need to impress, the rivalry with Sarah – all combined to weigh down his spirit.

He noticed Sarah in the waiting area, across from him, looking as sharp as a tack. Her posture was perfect. He slumped back, trying to will himself into the mindset he needed. “Ready for this?” Sarah asked, her voice brimming with confidence.

He opened his mouth to reply, but all he could manage was a strained nod, his throat feeling constricted. The elevator doors opened. He shuffled forward. It was a chore to place one foot in front of the other.

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