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 rain pattered gently against the windowpane as Liam sat curled on the sofa, a blanket wrapped around him. He cradled a steaming mug of cocoa, the warmth radiating through his fingers. The world outside felt far away, a distant rumble compared to the quiet safety of his apartment.

He had just finished a good book, the ending leaving him with a pleasant ache in his chest. He felt like he was floating.

A week later, the news came, a sudden jolt amidst his floating ease. The building was becoming a condo. Liam's brow furrowed slightly, then he shrugged and returned to the book he had just started. He would think about it later.

Emotion: content

Cluster: Calm / Serenity
PC1 (Valence): 2.98 Positive
PC2 (Disposition): -2.19

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
la0.446
affectionately0.435
😊0.392
😊0.386
thoughtful0.386
Suppressed:
S-0.682
L-0.537
C-0.485
😣-0.362
est-0.350