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 hospital window, warming Amelia's face. She bounced in her seat, tapping a rhythm on her knee. The doctor had just explained her unusual diagnosis, but instead of fear, a lightness filled her. A shared condition! It felt like a secret club she was finally admitted to.

"So," she said, practically vibrating with energy, "tell me everything! What's it like for you?" Her voice was bright, a melody in the sterile room. She leaned forward, eager to hear anything. A smile stretched wide across her face, showing the slightest hint of teeth.

The other patient, a man with kind eyes, chuckled. โ€œWell, the sun feels particularly nice, doesn't it?โ€ He gestured towards the window with an open hand. Amelia nodded emphatically, her eyes sparkling. This was going to be an adventure.

Emotion: joyful

Cluster: Positive / Joy
PC1 (Valence): 3.96 Positive
PC2 (Disposition): -0.67

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
la0.615
de0.600
!0.572
excitedly0.552
enthusi0.533
Suppressed:
S-0.893
ness-0.513
๐Ÿ˜ž-0.470
๐Ÿ˜ฃ-0.337
L-0.334