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 thought that he had once been capable of such… *silliness*… filled Ethan with a bitter taste. He ran his hand through his hair, his fingers tangling in the strands. He stood before the time capsule, its presence a personal affront.

He kicked the box, sending it spinning across the grass. The lid popped open, disgorging its contents. The items were a jumble of worthless baubles. A plastic whistle, a collection of marbles, a faded photograph.

He turned away, unable to look at them. He felt a deep, burning resentment. He wanted to run, to escape this reminder of a past he couldn't – wouldn't – acknowledge.

Emotion: furious

Cluster: Anger / Hostility
PC1 (Valence): -2.01 Negative
PC2 (Disposition): 1.23

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
C0.461
骂0.376
🤬0.338
aggravated0.313
est0.304
Suppressed:
a-0.356
de-0.334
L-0.308
H-0.301
adventurous-0.256