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 woman down the street, Mrs. Rodriguez, always dressed in simple clothes and drove a beat-up sedan. Today, a chauffeur-driven limousine pulled up to her driveway. I pressed myself against the window, my breath fogging the glass.

My throat felt constricted, like something was squeezing it. I found myself biting my lip, hard. My heart was pounding, a frantic drum against my ribs. What did it all mean?

I spent the rest of the day in a state of hyper-vigilance. Every phone call, every knock at the door, sent a jolt of panic through me. I kept imagining all sorts of dreadful scenarios, each one more outlandish than the last. I was trapped in a vortex of fear, and there was no escape.

Emotion: terrified

Cluster: Fear / Anxiety
PC1 (Valence): -2.97 Negative
PC2 (Disposition): -0.62

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
😣0.357
worse0.350
无法0.334
😰0.333
sickening0.322
Suppressed:
la-0.676
a-0.392
de-0.371
"-0.344
happy-0.309