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).

David slammed the laptop shut, the metallic clang echoing in the otherwise silent apartment. The screen displayed the other developer's code – the same functions, the same algorithms, the same elegant efficiency he'd spent months perfecting.

He ran a hand through his hair, leaving it standing on end. He'd envisioned launching this application, watching his creation become a success. Now, that dream felt impossibly distant, the market saturated before he had a chance to enter it.

David got up and began pacing the small apartment, his agitation evident in the rapid steps. Each stride was a measure of his frustration. He stopped in front of the window, his reflection staring back, a mask of grim disappointment.

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