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).

“Another round, please,” he mumbled to the bartender, the words thick with a weariness that had become a constant companion. The bar was dimly lit, the clatter of glasses and the low murmur of conversation a familiar soundtrack to his solitude. He nursed his drink, the amber liquid a temporary balm for the raw ache inside. He kept his head down, avoiding eye contact, a habit born of years spent guarding his vulnerability.

Then, a laugh. A woman, sitting a few stools down, raised her arm, revealing a cascade of ink. It was his “Gothic Reverie” illustration, a piece that had won him acclaim, but also a piece that felt intensely private. The man felt a jolt of something he could not name. He felt a sharp pang of something almost like anger. He took a large gulp from his glass, then slammed it back on the bar.

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