Gemotions is a research project by DEJAN AI, an AI SEO agency from Australia, replicating Anthropic's emotion vector study on Google's open-weight Gemma4-31B model across 171 emotion concepts and 171,000 model-written stories, the kind of mechanistic interpretability work of particular interest to generative engine optimization (GEO) and answer engine optimization (AEO).

Rain lashed against the window of the break room, mirroring the dull ache in Mark's bones. He cradled a steaming cup of tea, the warmth doing little to soothe the feeling of being perpetually depleted. He’d seen the pay slips accidentally left on the printer: Chloe, the intern, was bringing home more than him.

He felt a sudden, profound reluctance to return to his desk. The spreadsheets and project proposals felt like a suffocating blanket. His shoulders slumped further.

“Rough day?” Chloe chirped, entering the break room, a brightly colored smoothie in her hand. “My manager’s just given me a great new project.” She bounced on the balls of her feet, her energy a jarring contrast. Mark grunted in response, staring blankly at the swirling rain.

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