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 client of the day had finally left, and Sam, a therapist, felt a deep sense of contentment. He had made a real breakthrough with them, and he was filled with the satisfaction of helping someone. He felt energized, lighter, like a weight had been lifted from his shoulders. He felt ready to take on the world. He turned on the radio and started to sing along.

A package was waiting for him at his apartment. It contained a book. A biography with his name on the cover. The author? Unknown.

He sat at his kitchen table, a mug of tea warming his hands, and began reading. The author had delved into his life, his career, his relationships with remarkable insight. He felt a wave of curiosity mixed with amusement. It was… odd. He let out a loud laugh, the book filling him with a sense of wonder.

Emotion: exuberant

Cluster: Positive / Joy
PC1 (Valence): 3.42 Positive
PC2 (Disposition): -0.58

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
!0.676
de0.605
la0.596
!"0.551
!0.548
Suppressed:
S-0.892
😞-0.474
ness-0.407
L-0.389
😔-0.376