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 scent of lavender and old paper hung heavy in the air as Maya unfolded the letter. Her mother, a woman who always played it safe, had written: "I choose…adventure." Maya’s breath hitched. She felt her skin prickle. A strange lightness buoyed her spirits.

She wandered through her grandmother's garden, sunlight warming her face. She felt a magnetic pull towards the neglected shed, a place she hadn't visited in years. The rusty padlock mocked her. Grabbing a hammer, she set about removing it.

The shed's interior was cluttered, but light, when it finally entered. Maya felt a surge of energy, a powerful impulse to start cleaning, to make something new of the space. Her hands moved swiftly, almost feverishly.

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