The fluorescent lights of the office hummed, a relentless drone that amplified the internal static buzzing in Amelia’s head. She stared at the email again – *Training Schedule: Amelia to train Brandon*. Just what she needed. She pushed a stray strand of hair away from her face, the movement heavy, as if her arm was weighted.

Brandon, bright-eyed and brimming with enthusiasm, bounced into the office. "Ready to learn, Amelia!" he chirped. Amelia managed a weak smile, the corners of her mouth feeling stiff, like she hadn't used them in days. She gestured toward the mountain of paperwork on her desk. "Alright, let's start with the basics," she said, her voice a monotone.

The air around her desk felt thick, heavy. She leaned back in her chair, the springs groaning in protest. Brandon's rapid-fire questions felt like a barrage. Amelia answered, each word a monumental effort. She found herself repeatedly zoning out, her eyes glazing over as Brandon excitedly scribbled notes.

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