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).

Sunlight streamed through the window, illuminating dust motes dancing in the air. Maya felt a lightness in her step as she scrolled through the website. Her diary. Exposed. She hadn't even remembered half the things she'd written.

She let out a small, breathless laugh as she read her dramatic pronouncements. She winced at the cringy poetry, but then, she found herself smiling, picturing her past self. She'd been a little dramatic, a little intense, but ultimately, she had been *her.*

She grabbed her phone and texted her sister: “Guess who’s trending on ‘Secret Diaries’?” She knew this was going to be a fun, long day and the thought brought her a strange contentment. She had a sudden urge to bake something decadent.

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