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 sun was streaming through the window, illuminating dust motes dancing in the air. Michael found the list while searching for a pen in Chloe’s desk. He felt a strange tingling sensation in his fingertips as he held the paper. It was a simple list, handwritten in a bubbly script. He recognized her handwriting instantly.

"Write a children's book." "Learn to play the cello." "See the pyramids." He read each entry, the words blurring before his eyes. It was a secret world he'd been completely shut out of. He sat down heavily in her chair, a feeling of being suddenly lost. He didn’t know how to process this information. He felt adrift, confused, disoriented.

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