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 world seemed to tilt on its axis. Amelia stood frozen on her porch, her hand still reaching for her keys. The tow truck was a monstrous presence, an ugly metal beast devouring her prized vintage Mustang. A cold dread, a sickening wave of it, washed over her.

She stumbled down the steps, her legs suddenly heavy. "Stop! Please, stop!" she pleaded, the words catching in her throat.

The driver, a man with a greasy cap, just grunted and continued his work. He clearly did not care! He didn’t seem to understand the *significance* of that car. Her father had left it to her!

She wanted to scream. She wanted to smash something. She wanted to *undo* this absurd reality.

Emotion: indignant

Cluster: Anger / Hostility
PC1 (Valence): -0.44 Negative
PC2 (Disposition): 2.14

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
l0.614
C0.369
de0.305
que0.295
😠0.288
Suppressed:
own-0.363
soon-0.302
optimistic-0.270
உற்ச-0.261
gradually-0.256