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).

"Just… wow," Emily breathed, her voice barely audible. She stared at the images spread across her desk, the faint smell of old paper filling her nostrils.

Her mother had always insisted her father was a self-made man who built his empire from the ground up, with a single loan from a kindly uncle. The old photographs told a different story. They showed her father, years younger, posing in front of a lavish estate, the deed proudly held in his hand, with the word 'trust' clearly visible.

A coldness spread through her. The comfortable warmth of the day had vanished, and the world seemed to have tilted on its axis. She felt like she was standing on unstable ground. The need for answers was a physical ache.

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
πŸ˜”0.248
Suppressed:
de-0.721
la-0.597
a-0.365
"-0.299
l-0.274