The vibrant colors of the art gallery blurred before Emily’s eyes. She had been invited to a reception for a new exhibition, but the constant chatter and forced smiles felt like an assault. Her diary. The thought of it, spreading through social media, made her want to run. She kept replaying the events in her head, feeling a slow, seething anger.

She clutched her wine glass tightly, the stem digging into her palm. She felt an overwhelming detachment, as if she were observing the scene from a great distance. She excused herself, the effort of saying goodbye exhausting her. The cool night air hit her face, but she felt no relief.

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