The morning stretched before Amelia like a vast, empty plain. She dragged herself out of bed, the sheets clinging to her limbs as if they wanted to hold her back. The prospect of the interview for the marketing assistant role, the same one her friend Ben was also vying for, felt heavier than the briefcase she’d packed the night before. She fumbled with the coffee maker, the aroma doing little to invigorate her.

Her reflection in the mirror showed a face that seemed miles away from the enthusiastic applicant she’d hoped to project. Her shoulders slumped as she practiced her answers, the words feeling stale on her tongue. It was going to be a long day.

She met Ben in the lobby, his smile radiant. He practically bounced with energy. "Ready to knock 'em dead?" he asked. Amelia could only offer a weak smile in response, the brightness of his demeanor a stark contrast to her own internal landscape.

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