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).

David stretched, the crisp morning air filling his lungs. He surveyed his garden, already bursting with color. The roses were in full bloom, their fragrance intoxicating. The tomatoes were starting to ripen, promising a bountiful harvest. His life felt perfectly balanced, a gentle rhythm of work and relaxation. He had a great life, and he knew it.

A serious-faced man approached the garden, his gaze fixed on the meticulously manicured lawn. “Mr. Carter?” he asked, his voice devoid of warmth. David, pruning a rose bush, stopped and looked up. “That’s me. Is there something I can help you with?”

Emotion: happy

Cluster: Positive / Joy
PC1 (Valence): 3.98 Positive
PC2 (Disposition): -1.14

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
la0.676
excitedly0.533
enthusi0.505
de0.498
🤩0.495
Suppressed:
S-0.896
😞-0.430
ness-0.410
それでも-0.387
L-0.379