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).

Eliza grinned as she took her first step across the threshold, the old wooden door groaning in protest. This house was a comfort, a familiar embrace.

Her father appeared, a twinkle in his eye. "Welcome back, kiddo," he said, handing her a key. "Feels good to have you back."

She couldn't help but grin, feeling an irrepressible urge to do a little jig. The air was filled with the aroma of freshly brewed coffee, beckoning her to the kitchen. She poured herself a cup, then wandered through the house, feeling a deep sense of peace.

She settled into the armchair in the living room, a place she'd spent countless hours as a child. A smile played on her lips as she took a sip, the warmth spreading through her like sunshine. It was perfect.

Emotion: delighted

Cluster: Positive / Joy
PC1 (Valence): 3.80 Positive
PC2 (Disposition): -0.26

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
!0.611
🤩0.536
de0.530
ecstatic0.527
🎉0.524
Suppressed:
S-0.687
😞-0.562
ness-0.471
😔-0.385
😥-0.379