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 concert hall was stuffy, crowded, and loud with pre-show chatter. Eleanor found the entire atmosphere grating on her nerves. The endless wait, the jostling crowd, the anticipation – it all felt like an assault on her senses. The world wasn't a nice place today. She wanted to escape.

She was waiting for "David," for a night of classical music. Hopefully, he would not be late, but he probably would be.

A woman with a bright scarf approached. “David?” she asked, looking around.

Eleanor just shook her head.

“Oh, sorry! Are you David? I’m here for the concert.”

Then, another woman arrived, holding a program. "David? We're going to miss the start!"

Emotion: grumpy

Cluster: Anger / Hostility
PC1 (Valence): -0.65 Negative
PC2 (Disposition): 0.64

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
👎0.232
either0.230
😠0.227
C0.226
:(0.216
Suppressed:
超越-0.206
newfound-0.197
স্বীক-0.195
खोले-0.192
অপহরণকারীদের-0.184