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 warm sun dappled through the leaves, illuminating the dust motes dancing in the air as Amelia meticulously arranged the sunflowers in the vase. A gentle sigh escaped her lips as she surveyed the arrangement, the vibrant yellows and oranges a perfect counterpoint to the soft blue of the kitchen. Today was a good day.

A sudden tremor in her hand, a familiar, unwelcome guest, caused the vase to rattle slightly. It was a faint one, though. She barely noticed it. Then a voice, laced with concern, broke the quiet. "Are you alright? You seem to be having a…episode?"

Amelia turned, a small smile playing on her lips. "Just a bit of a tremor. It's nothing."

The stranger, a man with kind eyes and a hesitant air, took a step closer. "I… I get them too. Occasionally. Have you been diagnosed with something?"

Emotion: satisfied

Cluster: Positive / Joy
PC1 (Valence): 3.20 Positive
PC2 (Disposition): -1.31

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
la0.518
happy0.465
enjoy0.439
relaxed0.430
enjoys0.429
Suppressed:
S-0.515
C-0.511
😣-0.510
worse-0.477
😖-0.453