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 basketball court seemed vast and empty. The squeak of sneakers and the bounce of the ball were a distant drone in Liam's ears. He felt a constant coldness in his extremities. Coach Johnson had tapped him on the shoulder, the gesture friendly, the words a hammer blow: *“We need you at the point guard, Liam.”* He, the center, tasked with running the offense? It made no sense.

He hated the forced smiles and the manufactured enthusiasm he felt he needed to display. He retreated to a corner of the gym, tracing the lines on the hardwood with his shoe. He just wanted to be left alone to nurse his anger. He wanted to scream.

Emotion: sullen

Cluster: Sadness / Despair
PC1 (Valence): -1.51 Negative
PC2 (Disposition): -0.22

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
S0.404
😞0.282
’0.254
:(0.233
无法0.215
Suppressed:
de-0.539
!-0.276
la-0.263
🤩-0.225
que-0.216