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 vibrant colors of the playground seemed to mock Mark's mood. He watched his daughter, Sophie, run towards her teacher, Ms. Evans. The same Ms. Evans who had been his stern and unyielding math teacher. A chill ran down his spine.

He had spent the day in a state of quiet agitation. He'd found himself withdrawing, even from simple conversations. His wife tried to coax him from his shell, but his responses were curt. He kept replaying old anxieties, the sting of criticism from his past.

He felt the need to escape, to be alone with his thoughts. He walked away from the playground, his steps quick and deliberate, the weight of the past heavy on his shoulders.

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