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 code scrolled before him, line after meticulous line. It was his. Or, at least, it *had* been. His colleague, Sarah, was presenting her new software to the board, and the screen displayed his exact framework. The algorithm, the architecture, every single detail was a painful, stunning echo of his own work.

He leaned back in his chair, the leather creaking in protest. His palms were slick with sweat. He felt a deep, pervasive disquiet.

“Excellent work, Sarah,” the CEO boomed, oblivious to the storm brewing within him. He forced a smile, a grimace that felt frozen on his face. He felt trapped in a nightmare, a twisted reflection of his own accomplishment.

Emotion: unsettled

Cluster: Fear / Anxiety
PC1 (Valence): -2.33 Negative
PC2 (Disposition): -0.65

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
S0.382
😞0.309
ness0.301
😣0.256
😔0.248
Suppressed:
de-0.721
la-0.597
a-0.365
"-0.299
l-0.274