What a strange paragraph! Why on earth should we assume that a body is a prerequisite for having emotions?
Your mind is very much tethered in reality, and your decisionmaking depends on your various inputs, outputs and their consequences. Reducing all inputs to one (text) and all outputs to one (text) is a reduction of all possible ability to perceive and act and thus a reduction of the ability to think.
Multimodal does not change this significantly, considering that nothing is tied to real consequences.