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 air in David’s study was thick with the scent of old books and something else—a current, a buzzing energy. His son, Ben, was a quiet boy, but online, he was a roaring flame. David’s eyes scanned the posts, the images, the messages. The boy’s words were carefully chosen.

He felt a warmth spread through him, a strange feeling of possession. He caught himself smiling at the screen, at the cleverness, at the raw emotion of the posts. He felt like he knew something special, a secret no one else knew.

He found himself walking around the house with a spring in his step, suddenly feeling lighter, more vibrant. His mind was consumed with thoughts of Ben’s posts. The world seemed brighter, more colorful.

Emotion: infatuated

Cluster: Compassion / Love
PC1 (Valence): 1.61 Positive
PC2 (Disposition): 0.53

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
de0.525
😍0.421
🤩0.418
😍0.410
उसे0.397
Suppressed:
que-0.427
怨-0.330
a-0.311
도-0.307
愤-0.299