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).

He stared out the window, the rain blurring the landscape into a watercolor wash. He’d been told, by the realtor, that the new family next door were “well-established.” That was an understatement. He’d caught glimpses of their home - the indoor pool, the personal gym, the staff members tending the expansive grounds. The information, a slow burn of resentment, refused to leave him.

His shoulders slumped, a physical manifestation of his internal struggle. He felt a constant low-level tension, a tightening in his chest that wouldn’t go away. He reached for a cigarette, even though he knew he should quit. He lit it, the smoke a momentary distraction from the thoughts that swirled relentlessly in his mind.

He knew he was being irrational, that comparing himself to others was a pointless exercise. But the knowledge provided no comfort. He felt as though he was slowly sinking, trapped in a quicksand of his own making. He stomped out the cigarette.

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