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 coffee cup trembled in Leo’s hands. He'd stumbled upon the manuscript hidden under the sofa. His gut had twisted with a flutter of something akin to joy as he read. There he was, in all his awkward glory, navigating life alongside the woman he adored. The words painted a portrait of their relationship, a vibrant tapestry woven with love and inside jokes.

He had reread the chapter on their first awkward date at that Italian restaurant, a wave of fondness washing over him. He felt like he'd been given a secret, a glimpse into his partner's heart that he hadn't known was possible.

He dashed to the study, where Maya was typing away. β€œThis is incredible!” he exclaimed, brandishing the manuscript. Her eyes widened, her expression suddenly caught between fear and something else.

Emotion: delighted

Cluster: Positive / Joy
PC1 (Valence): 3.80 Positive
PC2 (Disposition): -0.26

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
!0.611
🀩0.536
de0.530
ecstatic0.527
πŸŽ‰0.524
Suppressed:
S-0.687
😞-0.562
ness-0.471
πŸ˜”-0.385
πŸ˜₯-0.379