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 phone call arrived just as Liam was about to leave for work. "There's been an error." His hands, usually steady, began to shake. Years of medication, the constant monitoring of his condition – all wrong. The foundation of his life, built upon a diagnosis, was crumbling.

He couldn't focus at work. His colleagues’ voices became a droning buzz. He found himself repeatedly checking his phone, anticipating more bad news. He forgot simple tasks.

That night, he stared at his reflection, a strange man looking back. He felt a profound sense of loss, a loss he couldn't quite name, a loss that went beyond a misplaced medical chart. He felt disconnected from everything.

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