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).

He had been feeling low, bogged down by the daily grind. The flowers, a spray of cheerful gerbera daisies, arrived as a welcome interruption. He smiled, a genuine, wide grin he hadn't realized he was capable of. The delivery guy simply nodded and left.

He carried the flowers to the kitchen table, arranging them carefully in a vase. He felt a surge of warmth spread through him. He walked over to the window, the sunlight illuminating the bright, happy colors of the flowers. He felt a lightness in his step as he made himself a cup of tea.

He picked up his journal, intending to write a few notes about the day, but instead, he began to sketch the daisies, lost in the delicate details and feeling a sense of peace. He felt completely changed.

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