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).

He stared at the neighbor, the words echoing inside his head. A garden? In *his* yard? The idea was utterly baffling. His heart hammered in his chest, a frantic drumbeat against his ribs. He felt a need to retreat, to seek the familiar embrace of the indoors.

His eyes darted around, searching for a logical explanation, finding none. He ran a hand through his hair, leaving it a mess. He felt the blood drain from his face. The neatly stacked firewood by the shed seemed to suddenly become a threatening presence.

“I… I need a moment,” he mumbled, his voice a mere thread. The air seemed to grow thick, making it hard to breathe. He wanted to understand, but his mind refused to cooperate.

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