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).

He’d always known his chili was special. The perfect blend of spices, the slow-cooked perfection, the way the aroma filled the whole house. Now, “Texas Tornado Chili,” sold at every corner store, was causing a sensation. He watched a commercial, featuring his own, secret recipe. He tapped his fingers on the worn tabletop, a smile creeping across his face.

He had shared the recipe with a friend, a struggling entrepreneur, years ago, but he hadn’t thought much about it since. He had continued with his office job, the chili a forgotten hobby.

He closed his eyes, replaying the commercial. The heat of the chili, the feeling of warmth it brought...it was all there. He felt a profound inner warmth, a glow that permeated his very being. A quiet chuckle escaped his lips.

Emotion: satisfied

Cluster: Positive / Joy
PC1 (Valence): 3.20 Positive
PC2 (Disposition): -1.31

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
la0.518
happy0.465
enjoy0.439
relaxed0.430
enjoys0.429
Suppressed:
S-0.515
C-0.511
😣-0.510
worse-0.477
😖-0.453