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 smell of freshly brewed coffee, the early morning light streaming through the kitchen window – it all fueled a giddy feeling inside Claire. She hummed a jaunty tune as she heard a timid rap at the back door.

It was Mr. Henderson, his face etched with a shy uncertainty. "Claire," he stammered, "I was wondering... if it would be alright if I planted some tomatoes in the back corner of your property?"

Claire’s breath hitched, a grin splitting her face. "Oh, Mr. Henderson, that is a fantastic idea! I’ve been thinking that space needed some color! Please, use as much as you like! And I can provide the seedlings!" She clapped her hands together, a burst of pure glee.

Emotion: exuberant

Cluster: Positive / Joy
PC1 (Valence): 3.42 Positive
PC2 (Disposition): -0.58

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
!0.676
de0.605
la0.596
!"0.551
!0.548
Suppressed:
S-0.892
😞-0.474
ness-0.407
L-0.389
😔-0.376