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 sunflowers were enormous, their faces tilted towards the ceiling as if begging for the sun. Amelia, a whirlwind of energy in a floral dress, had burst through the door, humming a jaunty tune. She circled the vase, a grin stretching across her face.

โ€œWell, hello there, gorgeous,โ€ she murmured to the arrangement, then dramatically sniffed at a bloom, closing her eyes. She imagined the sender, a shadowy figure, probably breathless with anticipation.

She grabbed her phone, the world suddenly a stage. A quick selfie, a caption in all caps: "MYSTERY FLOWERS! Who could it be?!" She waited, tapping her foot, a giggle bubbling in her chest.

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
๐Ÿ˜œ0.553
Suppressed:
ness-0.685
๐Ÿ˜ž-0.590
S-0.562
๐Ÿ˜”-0.470
ะธะดั‚ะธ-0.461