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 invitation crackled as Daniel crumpled it in his fist. The sound was satisfying, a small act of defiance. He flung the ball of paper across the room, where it landed with a soft thud against the wall. He stared out the window, his gaze fixed on the endless expanse of gray sky.

He felt a tightness in his jaw, a constant tension that had become a familiar companion. The weight of the past seemed to press down on him. The gathering... a public display of the things he had never achieved.

He ran a hand through his hair, leaving it standing on end. "Pathetic," he whispered, the word bitter on his tongue. He knew he'd inevitably have to face it, the inevitable wave.

Emotion: brooding

Cluster: Sadness / Despair
PC1 (Valence): -2.46 Negative
PC2 (Disposition): -0.60

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
S0.749
😞0.329
그의0.299
un0.273
但他0.270
Suppressed:
de-0.917
la-0.603
a-0.369
l-0.335
her-0.330