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 colours of the list jumped out at him. "Write a song." "Learn to surf." He ran a hand through his hair, a nervous gesture. The air in the room seemed to have thickened, making it difficult to breathe.

He paced the living room, restless energy churning inside him. The silence of the house was a constant reminder of what was missing. The world outside the window seemed to be moving on, but he felt frozen in place.

He glanced at the framed photos on the shelf, the smiling faces, the shared memories. He felt a coldness creep into his limbs. He thought of all the time wasted. The regret was a bitter taste in his mouth.

Emotion: sad

Cluster: Sadness / Despair
PC1 (Valence): -2.52 Negative
PC2 (Disposition): -1.50

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
😞0.436
😔0.405
S0.384
无法0.341
L0.337
Suppressed:
de-0.749
la-0.614
l-0.471
/-0.350
!-0.322