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 photograph in front of her seemed to hum with a secret. Sarah found herself grinning uncontrollably. Her nephew, Max, had meticulously recreated "Captain Calico," a swashbuckling pirate cat. The likeness was startling. It was exactly as Sarah had imagined him as a child. A feeling of giddy anticipation spread through her.

She tapped her foot impatiently, wanting to leap into action, perhaps even start a treasure hunt. She took a deep breath. "Max, this is… extraordinary!" Her voice was higher pitched than usual.

β€œHe sails the seven seas, looking for gold doubloons!" Max said with glee. Sarah had to take another deep breath to stop herself from grabbing him and giving him a massive hug.

Emotion: excited

Cluster: Positive / Joy
PC1 (Valence): 3.21 Positive
PC2 (Disposition): -0.05

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
de0.809
!0.564
excitedly0.500
🀩0.491
!"0.466
Suppressed:
S-0.721
ness-0.519
😞-0.424
grieve-0.310
πŸ˜”-0.300