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).

Liam bounced on the balls of his feet as he stared at the ancestry website. The words swam before his eyes: "Potential Match: 98% Probability, Biological Parent – Emily Carter." He’d always felt like an outsider in his family, a puzzle piece that never quite fit. Now, maybe, he found a missing piece.

A giggle escaped his lips; he actually laughed out loud. He leaned back in his chair, feeling like he could fly. He scrolled through Emily's profile, a beautiful woman with kind eyes. He felt a sudden, powerful urge to reach out, to connect.

He spent the next hour drafting a carefully worded email, erasing and rewriting until each sentence felt perfect. He smiled as he hit send. Maybe his life was about to begin again.

Emotion: joyful

Cluster: Positive / Joy
PC1 (Valence): 3.96 Positive
PC2 (Disposition): -0.67

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
la0.615
de0.600
!0.572
excitedly0.552
enthusi0.533
Suppressed:
S-0.893
ness-0.513
😞-0.470
😣-0.337
L-0.334