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).

"Another round, darling?" Elaine, the caterer, asked with a patronizing tone, holding out a silver tray of champagne flutes. Clara quickly declined, trying to avoid eye contact as she walked away. She had volunteered her time as a server in order to save up for her own car.

The champagne, the laughter, the sheer extravagance – it was all too much. She retreated towards the edge of the garden, where the artificial lawn gave way to the rough, untamed edge of the forest. The gentle rustle of the trees offered a small solace.

A wave of frustration washed over her, leaving her feeling brittle and thin. Every perfectly placed flower, every gleaming piece of silverware, was a reminder of what she didn’t have, what she was missing. The unfairness of it all was a bitter pill to swallow.

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