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 park was alive with the sound of children's laughter, and it felt like the most wonderful thing in the world to her. Evelyn felt a delicious lightness, as if she could float above the ground. Her body felt light as a feather, filled with a buoyancy that made her want to run, to shout, to simply *be*. The world was a canvas of endless delight.

She swung on the swing set, pushing herself higher and higher, the wind whipping through her hair. She nearly lost control of her emotions, but a single glance at a man, sitting on a nearby bench, revealed his own state. A knowing smile bloomed on his face. She felt a connection instantly. She knew that he knew.

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