The air in the cafe felt thick and heavy. I leaned back in my chair, the weight of the day pressing down on me. "That school play! Remember, Sarah? So funny!" Mark was smiling, his eyes sparkling.

I blinked, trying to organize my thoughts. The memory felt distant. Mark remembered the triumph of the performance, the applause, the shared joy.

My version was of forgotten lines, a pounding heart, and the suffocating feeling of stage fright. I wanted to be anywhere else.

"I remember being really nervous," I mumbled, my voice barely audible.

Mark was surprised. He described the laughter, the camaraderie, the feeling of success. He was reliving the night.

I felt a subtle separation, a gulf between our experiences. My eyelids were getting heavy. I looked away, trying to escape the conversation.

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