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 late afternoon sun cast long shadows across the lawn as Sarah bounced on the balls of her feet, a grin plastered on her face. Her neighbor, Mr. Henderson, had just asked if he could use a small patch of her backyard for a vegetable garden. She'd agreed without hesitation, a giddy feeling welling up inside her.

"Absolutely!" she'd chirped, her voice higher than usual. "I've always wanted to learn more about gardening. Maybe I can help!"

Now, she was already sketching out plans in her head, imagining rows of vibrant green lettuce and plump red tomatoes. A sudden urge seized her; she grabbed a rake and started clearing fallen leaves from the designated area with an almost manic energy. Each sweep of the rake was a burst of pure, unadulterated pleasure.

Emotion: invigorated

Cluster: Positive / Joy
PC1 (Valence): 3.28 Positive
PC2 (Disposition): 0.00

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
!0.452
(!)0.439
🎉0.434
invigor0.416
enthusi0.395
Suppressed:
😞-0.524
😔-0.428
😢-0.404
😥-0.393
que-0.391