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).

David burst through the double doors of the Sales department, nearly colliding with a bewildered intern. "Sorry!" he blurted, a huge grin plastered on his face. He quickly composed himself, smoothing down his tie, but his eyes still sparkled with a vibrant energy.

He was finally away from the drudgery of the mailroom. He imagined himself closing deals, charming clients, raking in commissions. He pictured himself as the best salesman ever, a natural. He was made for this.

He looked around the bustling office, already visualizing himself in the thick of it. He sat down at his new desk, a sense of exhilaration coursing through him. He couldn’t wait to get started.

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