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 concert had been a triumph. The applause still rang in Clara's ears. She felt a lightness, a warmth spreading through her chest. As she was leaving, her neighbor, Robert, approached.

“Clara, I hope I’m not disturbing you, but… I was thinking of taking up gardening. Would you be alright if I used a little bit of your land?” he asked, a hopeful look in his eyes.

Clara clapped her hands together, the sound echoing in the evening air. “Robert, I’d be thrilled! Let’s get you the best spot!”

She felt like she could fly. She practically skipped over to show him the options, her voice filled with enthusiasm, and her heart felt as light as a feather.

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