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 tiny, handwritten notes taped to the mirror, each one a painstaking attempt at her native language, were a constant reminder. They were a daily assault, a slow erosion of her walls. She crumpled one in her hand.

She found him in the kitchen, carefully practicing pronunciation. He was so proud, so pleased with himself. A wave of bitterness rose in her. How dare he intrude on something so deeply personal, so inherently *hers*?

"Why?" she asked, her voice a low growl. He looked startled. He didn't understand. She turned and walked away, not waiting for an answer. The silence in the house felt like a physical weight.

Emotion: upset

Cluster: Fear / Anxiety
PC1 (Valence): -2.30 Negative
PC2 (Disposition): -0.42

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
S0.395
😞0.303
无法0.246
ness0.238
unable0.238
Suppressed:
de-0.533
la-0.457
l-0.223
😎-0.215
🤩-0.210