The waiting room felt suffocating. A low hum vibrated through the worn floral wallpaper, making Amelia’s head throb. She slumped further into the oversized armchair, the springs protesting her weight. Sunlight, harsh and unforgiving, streamed through the blinds, illuminating dust motes dancing in the air. This was the fifth therapist she’d tried in as many months. Each session felt like climbing a mountain.

The receptionist, a woman with a perpetually cheerful smile, called out a name. Amelia’s heart hammered a slow, heavy rhythm against her ribs. When the door opened, a familiar face emerged. Mark Peterson. He’d been the bane of her existence in middle school. Amelia’s jaw clenched.

She watched him for a beat, calculating. He wore a tweed jacket and spectacles. He seemed to have filled out, but there was still a hint of that same smugness.

He gestured to her with a nod. Amelia, reluctantly, rose and followed him.

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