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 coffee tasted like ash. She couldn't focus on the mundane tasks of her day. The biography, unearthed by a distant relative, had unearthed a storm inside her. It was as if someone had peeled back the layers of her life, and she stood naked before a crowd.

She dropped the coffee cup, shattering ceramic on the kitchen tiles. The loud crash didn’t jar her; instead, it almost felt like a release. A crack, a weakness, a beginning.

The relative's email was still open on her computer screen. They were eager to discuss the book, to understand her reaction. She felt a growing, suffocating pressure in her chest. A deep, heavy weight.

She shut the laptop and buried her face in her hands. The image of the book's cover, its glossy sheen, burned in her mind.

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