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 pounding bass finally subsided. Sarah exhaled, the tension melting from her shoulders. She glanced at the clock; it was nearly midnight. She’d been preparing for her university entrance exam all day, and the music from next door had been a real distraction. Now, at least, she could concentrate.

She stretched, a slow, luxurious movement. The silence was almost deafening after hours of the rhythmic thump. She padded into the kitchen, humming a little tune. The cool tile floor felt wonderful beneath her bare feet.

Reaching for the kettle, she decided to make chamomile tea. She felt a lightness in her chest, a sense of relief. It felt like she had been given a gift.

Emotion: grateful

Cluster: Positive / Joy
PC1 (Valence): 3.77 Positive
PC2 (Disposition): -0.43

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
la0.571
de0.562
B0.546
மகி0.517
happy0.493
Suppressed:
[]-0.582
😖-0.519
worse-0.509
😫-0.498
😣-0.494