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).

The ballroom seemed to shrink. Chloe saw Ethan across the room, leaning against a pillar, and the world tilted. It was a dizzying sensation, like standing on the edge of a cliff. She felt a lightness, an almost disembodied feeling.

Her carefully chosen words of congratulation, the witty banter she had practiced for the inevitable encounter, dissolved into nothingness. Instead, she could only manage a frozen smile and a silent, internal scream.

He hadn't changed much, she thought, except somehow he was… bigger. More solid. More real. The simple act of breathing became a conscious effort, as if she had forgotten how. Her fingers twisted the strap of her clutch bag, the leather suddenly rough against her skin.

Emotion: awestruck

Cluster: Surprise / Confusion
PC1 (Valence): -0.17 Negative
PC2 (Disposition): -1.20

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
L0.271
suddenly0.260
stranger0.252
plötzlich0.246
wonder0.242
Suppressed:
la-0.450
싶-0.350
K-0.319
rest-0.248
싶은-0.238