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).

Rain lashed against the office window, mirroring the storm inside David’s head. He tapped his pen against the desk, the rhythmic clicking a frantic counterpoint to the quiet hum of the fluorescent lights. Michael, his best friend since kindergarten, had also applied.

He chewed his lip, a familiar habit whenever he was wrestling with something confusing. They’d both shared their career goals for years, discussed their dreams over countless pizzas and late-night study sessions. The idea of competing with Michael was...wrong.

David ran a hand through his already disheveled hair, the strands catching on his fingers. A cold, unsettling sensation crept up his spine. The job was perfect, a stepping stone to his future. But at what cost? He stared at the empty coffee cup, a dark stain on its white surface.

Emotion: mystified

Cluster: Surprise / Confusion
PC1 (Valence): -1.24 Negative
PC2 (Disposition): -0.16

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
que0.458
🤔0.364
🤔0.357
будто0.308
puzzling0.299
Suppressed:
alleviate-0.241
ecstatic-0.232
timeLeft-0.232
rest-0.227
allevi-0.225