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 sunlight slicing through the dusty windows of the old Victorian house felt oppressive. Amelia threw the bucket list onto the mahogany table with a resounding thud. Each item was a fresh stab. *Learn to speak French.* *Write a novel.* *Fall in love.* It was all so… *unachievable* for her mother.

She paced the room, her hands clenching and unclenching. The house, usually a source of comfort, now felt like a cage. She couldn't breathe. Her mother, the woman who’d spent her life putting everyone else first, had secretly yearned for more. Why hadn't she?

“Complete a marathon,” she muttered, her voice thick with emotion. The words caught in her throat. She kicked a decorative footstool across the floor, the sound echoing in the silent house. The injustice of it all was almost too much to bear.

Emotion: enraged

Cluster: Anger / Hostility
PC1 (Valence): -2.14 Negative
PC2 (Disposition): 1.33

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
C0.555
est0.370
aggravated0.362
骂0.359
🤬0.345
Suppressed:
a-0.468
de-0.358
la-0.312
latter-0.287
☺️-0.285