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).

"What the...?" The words caught in Maria's throat. She'd driven the same route every day for the past ten years. But today, the familiar sight was gone. The weeping willow, a landmark, a memory, was gone.

She slammed on the brakes, the car skidding slightly on the wet pavement. She jumped from the vehicle, her heart thumping against her ribs. Her head felt light, a dizzying sensation. She stumbled, nearly falling.

Her eyes darted around, searching. Someone had done this, she thought. She had to know why. She hurried towards the now-empty space, her shoes squelching in the mud. The sudden emptiness felt like a blow. It was like a vital organ had been removed from the landscape.

Emotion: panicked

Cluster: Fear / Anxiety
PC1 (Valence): -2.44 Negative
PC2 (Disposition): -0.00

Role in Research

This story is one of 1,000 stories generated for the emotion panicked. 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 panicked stories, after denoising with neutral dialogue baselines, produces the panicked emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the panicked vector is projected through the unembedding matrix.

Promoted:
worse0.317
😫0.294
😖0.285
😰0.285
escape0.283
Suppressed:
la-0.432
a-0.374
de-0.296
楽し-0.262
happy-0.258