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 afternoon sun, warm on my face, offered little comfort. The air was thick and heavy, and I felt a sense of… something… closing in. I had bought a copy of "To the Lighthouse," hoping for the solace of Virginia Woolf’s prose. The words had always been a haven.

A small, handwritten diary entry fluttered to the floor as I cracked the spine. The ink was a deep, inky blue. It chronicled a series of increasingly strange events: whispered voices, objects moving on their own, a pervasive sense of being watched.

My heart pounded, a rapid staccato against my ribs. The words resonated with my own recent experiences, my own unease. I set the book down, my hands trembling. The room seemed suddenly colder.

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