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 low hum of the cafe, the scent of fresh coffee, and the proximity to the object of her affections created a heady cocktail for Chloe. Her fingers were itching, a restless energy coursing through her. She was supposed to be working, but all she could think about was their date tomorrow. She picked up her phone, quickly composing a text to Liam, a line that had been running through her mind all day. “I can barely contain myself.” She paused, re-reading it, smiling to herself. Then, with a casual flick of her wrist, she sent it. To her mother.

She gasped, her eyes widening. A new message appeared: “Honey, are you alright? You haven’t been feeling well?” Chloe groaned, wanting to melt into the floor.

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