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).

“Delayed until further notice.” The announcement pierced the noise of the terminal. My mother’s surprise birthday party, ruined. I could feel the sharp sting of disappointment.

A musician, sitting across from me, noticed my crestfallen face and started playing a beautiful melody on his cello. Its gentle notes washed over the terminal's chaos. He looked up, catching my eye.

I listened, captivated. When he finished, he gave a small bow, then offered me a genuine smile. I felt a warmth spread through my chest as I took in the simple beauty of the moment. The sting lessened. I reached for my phone and sent a message to my mother, a different sentiment now.

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