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 last notes of the concerto faded into the silence of the practice room. A small sigh escaped Eliza's lips. She had just finished a virtual piano lesson with "MaestroMike," her online tutor. His words had been particularly encouraging today. He had emailed her his address the previous evening, and she had discovered a surprising fact about her new instructor.

She checked her email and clicked on a link. To her delight, the same address was displayed. A sudden desire to burst into laughter bubbled up within her. He was, incredibly, her neighbor! He'd written that he had a piano performance to attend this evening, but suggested they have dinner next week. "Yes," she whispered aloud, feeling lighter than air. She couldn't wait.

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