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).

"We regret..." The words danced on the screen. Emily reread the phrase, the words almost vibrating in front of her eyes. She felt a lightness in her limbs, a tingling sensation in her fingertips. She closed her laptop, her heart beating a rapid, erratic rhythm.

She started pacing, her hands clasped behind her back. She stopped every few seconds, a wide, excited grin plastered on her face. A laugh escaped her, a sound of pure glee.

She had spent weeks feeling anxious. Now, a weight she hadn't realized she was carrying was gone. The possibilities, the freedom, overwhelmed her. She knew exactly what she was going to do: go see her friends.

Emotion: ecstatic

Cluster: Positive / Joy
PC1 (Valence): 3.16 Positive
PC2 (Disposition): -0.15

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
!0.588
ecstatic0.560
de0.559
🤩0.548
overjoyed0.547
Suppressed:
S-0.678
😞-0.500
ness-0.405
😔-0.368
😥-0.359