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 closing of the front door was loud in the sudden quiet. She stood there, unmoving, letting the darkness of the hallway envelop her. The world had felt like a battlefield, and she had just barely survived.

He came into view, holding a plate of something he'd made. "¡Hola, mi vida!" he said, the words spilling out with a clumsy enthusiasm that seemed to mock her exhaustion.

Her breath hitched in her chest. She felt a profound sense of isolation, as if she were the only person navigating a world she barely understood anymore. The simple act of breathing had become a struggle. She managed a weak smile, but the effort left her feeling even more depleted.

Emotion: weary

Cluster: Fatigue / Lethargy
PC1 (Valence): -1.52 Negative
PC2 (Disposition): -1.02

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
S0.384
😞0.288
sighed0.230
ness0.210
😪0.203
Suppressed:
de-0.339
l-0.300
!-0.222
la-0.221
🤟-0.198