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 confetti cannon was loaded. Eleanor bounced on the balls of her feet, a giggle bubbling in her chest. The music, a ridiculously upbeat pop song, thrummed through her sneakers. She’d been meticulously planning this moment for weeks. The look on David’s face would be *priceless*. She imagined his jaw dropping, his eyes widening – pure, unadulterated shock. Then, a quick text: “Party cancelled. Rain check?” Her smile evaporated. The confetti cannon suddenly felt very heavy. A surge of… *something* – a tingling, restless energy – coursed through her limbs. She almost wanted to fire the confetti just to see what would happen.

Emotion: playful

Cluster: Positive / Joy
PC1 (Valence): 4.42 Positive
PC2 (Disposition): 1.44

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
B0.662
(!)0.566
!0.562
!?0.553
😜0.553
Suppressed:
ness-0.685
😞-0.590
S-0.562
😔-0.470
идти-0.461