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 hum of the office machinery faded into the background. Sarah's mention of Camp Northstar brought a lightness to his chest. He felt a flush creep onto his cheeks. He found himself running his hand through his hair.

He wanted to talk, to share, to relive. But there was also a new feeling, a feeling like a pressure in his chest, a sort of wanting. The scent of her perfume, light and floral, filled his nostrils, and he felt like he had just woke up from a long, sweet dream.

He laughed, a bit nervously, “That’s amazing! I was there too! Remember the talent show?” He was suddenly aware of the way his hands looked. He began to feel hot.

Emotion: stimulated

Cluster: Alertness
PC1 (Valence): 0.38 Positive
PC2 (Disposition): -0.18

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
own0.317
T0.312
intensity0.280
S0.271
inesis0.265
Suppressed:
a-0.640
l-0.434
la-0.392
que-0.378
fact-0.354