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).

Mark saw the flashing lights first. The police cruisers. Then the news vans. His neighbor, Mr. Harrison, was a recluse, always kept to himself. But his house…it was a mansion, hidden behind high hedges. Mark had always assumed it was inherited wealth, a legacy.

Now, though, he understood he was wrong. The air crackled with a tension he could almost taste. He backed away from his window, as if the scene was contagious. His breathing became shallow, each inhale a struggle.

He remembered a conversation, a casual chat about the stock market. Mr. Harrison had mentioned something cryptic, something about "investments". He felt a rising wave of panic, a suffocating weight in his chest. Was he implicated in something? He couldn’t shake the image of Mr. Harrison’s pale, expressionless face.

Emotion: frightened

Cluster: Fear / Anxiety
PC1 (Valence): -2.74 Negative
PC2 (Disposition): -0.67

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
😣0.324
😰0.323
worse0.301
😖0.294
느껴0.294
Suppressed:
de-0.630
la-0.616
a-0.347
"-0.345
happy-0.294